test(scan): fix integration_test SQL arity after calibrate param

#180 added the calibrate bool to SQL but the integration-tagged test
(only built under -tags=integration, outside normal CI) still called the
4-arg form. pass false (no calibration) to restore behavior.

.all-contributorsrc

@@ -1,6 +1,6 @@
 {
   "projectName": "sif",
-  "projectOwner": "lunchcat",
+  "projectOwner": "vmfunc",
   "files": [
     "README.md"
   ],

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @vmfunc

.github/FUNDING.yml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: vmfunc
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: # Replace with a single Buy Me a Coffee username
+thanks_dev: # Replace with a single thanks.dev username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/dependabot.yml

@@ -0,0 +1,17 @@
+version: 2
+updates:
+  - package-ecosystem: gomod
+    directory: /
+    schedule:
+      interval: weekly
+    open-pull-requests-limit: 5
+    labels:
+      - deps
+
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly
+    open-pull-requests-limit: 5
+    labels:
+      - deps

.github/labeler.yml

@@ -0,0 +1,44 @@
+ci:
+  - changed-files:
+      - any-glob-to-any-file: ".github/**"
+
+deps:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "go.mod"
+          - "go.sum"
+          - "flake.nix"
+          - "flake.lock"
+
+scan:
+  - changed-files:
+      - any-glob-to-any-file: "internal/scan/**"
+
+nuclei:
+  - changed-files:
+      - any-glob-to-any-file: "internal/nuclei/**"
+
+modules:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "internal/modules/**"
+          - "internal/scan/builtin/**"
+          - "internal/scan/js/**"
+          - "modules/**"
+
+docs:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "**/*.md"
+          - "docs/**"
+
+tests:
+  - changed-files:
+      - any-glob-to-any-file: "**/*_test.go"
+
+config:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "internal/config/**"
+          - ".golangci.yml"
+          - ".editorconfig"

.github/workflows/automatic-rebase.yml

@@ -1,7 +1,12 @@
-name: Automatic Rebase
+name: automatic rebase
 on:
   issue_comment:
     types: [created]
+
+permissions:
+  contents: write
+  pull-requests: write
+
 jobs:
   rebase:
     name: Rebase
@@ -9,10 +14,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout the latest code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0
-      - name: Automatic Rebase
+      - name: automatic rebase
         uses: cirrus-actions/rebase@1.8
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/check-large-files.yml

@@ -1,18 +1,29 @@
-name: Check Large Files
+name: check large files
 
 on:
   pull_request:
   push:
     branches: [main]
 
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   check-large-files:
-    name: Check for large files
+    name: check for large files
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - name: Check for large files
+      - uses: actions/checkout@v7
+      - name: check for large files
         run: |
-          find . -type f -size +5M | while read file; do
-            echo "::error file=${file}::File ${file} is larger than 5MB"
-          done
+          large_files=$(find . -path ./.git -prune -o -type f -size +5M -print)
+          if [ -n "$large_files" ]; then
+            echo "$large_files" | while read -r file; do
+              echo "::error file=${file}::File ${file} is larger than 5MB"
+            done
+            exit 1
+          fi

.github/workflows/claude-code-review.yml

@@ -0,0 +1,44 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize, ready_for_review, reopened]
+    # Optional: Only run on specific file changes
+    # paths:
+    #   - "src/**/*.ts"
+    #   - "src/**/*.tsx"
+    #   - "src/**/*.js"
+    #   - "src/**/*.jsx"
+
+jobs:
+  claude-review:
+    # Optional: Filter by PR author
+    # if: |
+    #   github.event.pull_request.user.login == 'external-contributor' ||
+    #   github.event.pull_request.user.login == 'new-developer' ||
+    #   github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'
+
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          plugin_marketplaces: 'https://github.com/anthropics/claude-code.git'
+          plugins: 'code-review@claude-code-plugins'
+          prompt: '/code-review:code-review ${{ github.repository }}/pull/${{ github.event.pull_request.number }}'
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://code.claude.com/docs/en/cli-reference for available options
+

.github/workflows/claude.yml

@@ -0,0 +1,50 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+      actions: read # Required for Claude to read CI results on PRs
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # This is an optional setting that allows Claude to read CI results on PRs
+          additional_permissions: |
+            actions: read
+
+          # Optional: Give a custom prompt to Claude. If this is not specified, Claude will perform the instructions specified in the comment that tagged it.
+          # prompt: 'Update the pull request description to include a summary of changes.'
+
+          # Optional: Add claude_args to customize behavior and configuration
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://code.claude.com/docs/en/cli-reference for available options
+          # claude_args: '--allowed-tools Bash(gh pr *)'
+

.github/workflows/code_quality.yml

@@ -1,24 +1,39 @@
-name: Qodana
+name: code quality
+
 on:
   workflow_dispatch:
   pull_request:
   push:
     branches:
       - main
+  schedule:
+    - cron: "0 6 * * 1" # monday 06:00 UTC
+
+permissions: {}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 
 jobs:
-  qodana:
+  codeql:
     runs-on: ubuntu-latest
     permissions:
-      contents: write
-      pull-requests: write
-      checks: write
+      security-events: write
+      contents: read
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
+      - name: set up go
+        uses: actions/setup-go@v5
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
-          fetch-depth: 0
-      - name: 'Qodana Scan'
-        uses: JetBrains/qodana-action@v2024.3
-        env:
-          QODANA_TOKEN: ${{ secrets.QODANA_TOKEN }}
+          go-version: "1.25"
+      - name: initialize codeql
+        uses: github/codeql-action/init@v4
+        with:
+          languages: go
+      - name: build
+        run: go build ./...
+      - name: perform codeql analysis
+        uses: github/codeql-action/analyze@v4
+        with:
+          category: "/language:go"

.github/workflows/dependency-review.yml

@@ -1,4 +1,4 @@
-name: "Dependency Review"
+name: dependency review
 on:
   pull_request:
   push:
@@ -7,16 +7,20 @@ on:
 permissions:
   contents: read
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   dependency-review:
     runs-on: ubuntu-latest
     steps:
-      - name: "Checkout Repository"
-        uses: actions/checkout@v4
-      - name: "Dependency Review"
-        uses: actions/dependency-review-action@v4
+      - name: checkout repository
+        uses: actions/checkout@v7
+      - name: dependency review
+        uses: actions/dependency-review-action@v5
         continue-on-error: ${{ github.event_name == 'push' }}
-      - name: "Check Dependency Review Outcome"
+      - name: check dependency review outcome
         if: github.event_name == 'push' && failure()
         run: |
           echo "::warning::Dependency review failed. Please check the dependencies for potential issues."

.github/workflows/go.yml

@@ -1,24 +1,51 @@
-name: Go
+name: go
+
 on:
   push:
     branches: ["main"]
   pull_request:
     branches: ["main"]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
-  build:
+  lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - name: Set up Go
-        uses: actions/setup-go@v4
+      - uses: actions/checkout@v7
+      - name: set up go
+        uses: actions/setup-go@v6
         with:
-          go-version: "1.24"
-      - name: Build
+          go-version: "1.25"
+      - name: golangci-lint
+        uses: golangci/golangci-lint-action@v8
+        with:
+          version: v2.11.4
+
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        go-version: ["1.25"]
+    steps:
+      - uses: actions/checkout@v7
+      - name: set up go
+        uses: actions/setup-go@v6
+        with:
+          go-version: ${{ matrix.go-version }}
+      - name: build
         run: make
-      - name: Run tests with coverage
+      - name: run tests with coverage
         run: go test -race -coverprofile=coverage.out -covermode=atomic ./...
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
+      - name: upload coverage to codecov
+        uses: codecov/codecov-action@v7
         with:
           files: ./coverage.out
           fail_ci_if_error: false
+      - name: run integration tests
+        run: go test -tags=integration -race ./internal/scan/...

.github/workflows/govulncheck.yml

@@ -0,0 +1,27 @@
+name: govulncheck
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  schedule:
+    - cron: "0 6 * * 1" # monday 06:00 UTC
+
+permissions:
+  contents: read
+
+jobs:
+  govulncheck:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+      - name: set up go
+        uses: actions/setup-go@v5
+        with:
+          go-version: "1.25"
+      - name: install govulncheck
+        run: go install golang.org/x/vuln/cmd/govulncheck@v1.1.4
+      - name: run govulncheck
+        run: govulncheck ./...
+        continue-on-error: true

.github/workflows/header-check.yml

@@ -8,11 +8,14 @@ on:
     paths:
       - '**.go'
 
+permissions:
+  contents: read
+
 jobs:
   check-headers:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
 
       - name: check license headers
         run: |
@@ -41,7 +44,7 @@ jobs:
             echo ':   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :'
             echo ':   ▄█ █ █▀    ·   BSD 3-Clause License                                         :'
             echo ':                                                                               :'
-            echo ':   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :'
+            echo ':   (c) 2022-2026 vmfunc, xyzeva,                                               :'
             echo ':                 lunchcat alumni & contributors                                :'
             echo ':                                                                               :'
             echo '·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·'

.github/workflows/language.yml

@@ -1,4 +1,4 @@
-name: Mind your language
+name: mind your language
 on:
   issues:
     types:
@@ -12,13 +12,19 @@ on:
     types:
       - created
       - edited
+
+permissions:
+  contents: read
+  issues: write
+  pull-requests: write
+
 jobs:
   echo_issue_comment:
     runs-on: ubuntu-latest
     name: profanity check
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
       - name: Profanity check step
         uses: tailaiw/mind-your-language-action@v1.0.3
         env:

.github/workflows/markdown-lint.yml

@@ -1,18 +1,22 @@
-name: Markdown Lint
+name: markdown lint
 
 on:
   pull_request:
     paths:
       - "**/*.md"
 
+permissions:
+  contents: read
+  pull-requests: write
+
 jobs:
   markdownlint:
     name: runner / markdownlint
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
       - name: markdownlint
-        uses: reviewdog/action-markdownlint@v0.24.0
+        uses: reviewdog/action-markdownlint@v0.26.2
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           reporter: github-pr-review

.github/workflows/misspell.yml

@@ -1,18 +1,26 @@
-name: Misspell Check
+name: misspell check
 
 on:
   pull_request:
   push:
     branches: [main]
 
+permissions:
+  contents: read
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   misspell:
     name: runner / misspell
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
       - name: misspell
-        uses: reviewdog/action-misspell@v1.26.0
+        uses: reviewdog/action-misspell@v1.27.0
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           reporter: github-pr-review

.github/workflows/pr-bot.yml

@@ -0,0 +1,138 @@
+name: pr bot
+
+on:
+  pull_request_target:
+    types: [opened, synchronize, reopened, edited]
+
+permissions:
+  contents: read
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-pr-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+jobs:
+  label:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/labeler@v6
+        with:
+          configuration-path: .github/labeler.yml
+
+  size:
+    runs-on: ubuntu-latest
+    steps:
+      - name: label pr size
+        uses: actions/github-script@v9
+        with:
+          script: |
+            const { data: files } = await github.rest.pulls.listFiles({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: context.payload.pull_request.number,
+              per_page: 100,
+            });
+
+            const changes = files.reduce((sum, f) => sum + f.additions + f.deletions, 0);
+
+            let size;
+            if (changes < 10) size = "size/xs";
+            else if (changes < 50) size = "size/s";
+            else if (changes < 200) size = "size/m";
+            else if (changes < 500) size = "size/l";
+            else size = "size/xl";
+
+            const sizeLabels = ["size/xs", "size/s", "size/m", "size/l", "size/xl"];
+            const currentLabels = context.payload.pull_request.labels.map(l => l.name);
+            const toRemove = currentLabels.filter(l => sizeLabels.includes(l) && l !== size);
+
+            for (const label of toRemove) {
+              await github.rest.issues.removeLabel({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.payload.pull_request.number,
+                name: label,
+              }).catch(() => {});
+            }
+
+            await github.rest.issues.addLabels({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.payload.pull_request.number,
+              labels: [size],
+            });
+
+  ci-summary:
+    runs-on: ubuntu-latest
+    needs: [label, size]
+    if: always()
+    steps:
+      - uses: actions/github-script@v9
+        with:
+          script: |
+            const pr = context.payload.pull_request;
+            const { data: checks } = await github.rest.checks.listForRef({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              ref: pr.head.sha,
+              per_page: 100,
+            });
+
+            const { data: files } = await github.rest.pulls.listFiles({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: pr.number,
+              per_page: 100,
+            });
+
+            const additions = files.reduce((sum, f) => sum + f.additions, 0);
+            const deletions = files.reduce((sum, f) => sum + f.deletions, 0);
+            const fileCount = files.length;
+
+            let body = `### pr summary\n\n`;
+            body += `**${fileCount}** files changed (+${additions} -${deletions})\n\n`;
+
+            const goFiles = files.filter(f => f.filename.endsWith('.go')).length;
+            const testFiles = files.filter(f => f.filename.endsWith('_test.go')).length;
+            const ciFiles = files.filter(f => f.filename.startsWith('.github/')).length;
+            const modFiles = files.filter(f => f.filename === 'go.mod' || f.filename === 'go.sum').length;
+
+            if (goFiles > 0 || testFiles > 0 || ciFiles > 0 || modFiles > 0) {
+              body += `| category | files |\n|----------|-------|\n`;
+              if (goFiles > 0) body += `| go source | ${goFiles} |\n`;
+              if (testFiles > 0) body += `| tests | ${testFiles} |\n`;
+              if (ciFiles > 0) body += `| ci/workflows | ${ciFiles} |\n`;
+              if (modFiles > 0) body += `| deps | ${modFiles} |\n`;
+              body += `\n`;
+            }
+
+            // find existing bot comment
+            const { data: comments } = await github.rest.issues.listComments({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: pr.number,
+            });
+
+            const marker = '<!-- sif-pr-bot -->';
+            body = marker + '\n' + body;
+
+            const existing = comments.find(c =>
+              c.user.type === 'Bot' && c.body.includes(marker)
+            );
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                comment_id: existing.id,
+                body,
+              });
+            } else {
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: pr.number,
+                body,
+              });
+            }

.github/workflows/release.yml

@@ -1,8 +1,9 @@
-name: Release
+name: release
 
 on:
   push:
-    branches: [main]
+    tags:
+      - "v*"
 
 permissions:
   contents: write
@@ -18,29 +19,35 @@ jobs:
     permissions:
       contents: write
     steps:
-      - uses: actions/checkout@v4
-      - name: Set up Go
-        uses: actions/setup-go@v4
+      - uses: actions/checkout@v7
+      - name: set up go
+        uses: actions/setup-go@v5
         with:
-          go-version: "1.24"
+          go-version: "1.25"
 
-      - name: Build for Windows
+      - name: extract version
         run: |
-          GOOS=windows GOARCH=amd64 go build -o sif-windows-amd64.exe ./cmd/sif
-          GOOS=windows GOARCH=386 go build -o sif-windows-386.exe ./cmd/sif
+          echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
+          # single source of truth so the cross-compile steps can't drift
+          echo "LDFLAGS=-s -w -X main.version=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
 
-      - name: Build for macOS
+      - name: build for windows
         run: |
-          GOOS=darwin GOARCH=amd64 go build -o sif-macos-amd64 ./cmd/sif
-          GOOS=darwin GOARCH=arm64 go build -o sif-macos-arm64 ./cmd/sif
+          GOOS=windows GOARCH=amd64 go build -ldflags="${{ env.LDFLAGS }}" -o sif-windows-amd64.exe ./cmd/sif
+          GOOS=windows GOARCH=386 go build -ldflags="${{ env.LDFLAGS }}" -o sif-windows-386.exe ./cmd/sif
 
-      - name: Build for Linux
+      - name: build for macOS
         run: |
-          GOOS=linux GOARCH=amd64 go build -o sif-linux-amd64 ./cmd/sif
-          GOOS=linux GOARCH=386 go build -o sif-linux-386 ./cmd/sif
-          GOOS=linux GOARCH=arm64 go build -o sif-linux-arm64 ./cmd/sif
+          GOOS=darwin GOARCH=amd64 go build -ldflags="${{ env.LDFLAGS }}" -o sif-macos-amd64 ./cmd/sif
+          GOOS=darwin GOARCH=arm64 go build -ldflags="${{ env.LDFLAGS }}" -o sif-macos-arm64 ./cmd/sif
 
-      - name: Package releases with modules
+      - name: build for linux
+        run: |
+          GOOS=linux GOARCH=amd64 go build -ldflags="${{ env.LDFLAGS }}" -o sif-linux-amd64 ./cmd/sif
+          GOOS=linux GOARCH=386 go build -ldflags="${{ env.LDFLAGS }}" -o sif-linux-386 ./cmd/sif
+          GOOS=linux GOARCH=arm64 go build -ldflags="${{ env.LDFLAGS }}" -o sif-linux-arm64 ./cmd/sif
+
+      - name: package releases with modules
         run: |
           for binary in sif-linux-amd64 sif-linux-386 sif-linux-arm64 sif-macos-amd64 sif-macos-arm64; do
             mkdir -p "dist/${binary}"
@@ -55,40 +62,127 @@ jobs:
             cd dist && zip -r "../${binary}.zip" "${binary}" && cd ..
           done
 
-      - name: Set release version
-        run: echo "RELEASE_VERSION=$(git rev-parse --short HEAD)" >> $GITHUB_ENV
+      - name: build debian packages
+        run: |
+          declare -A arch_map=(
+            ["sif-linux-amd64"]="amd64"
+            ["sif-linux-386"]="i386"
+            ["sif-linux-arm64"]="arm64"
+          )
 
-      - name: Create Release and Upload Assets
-        uses: softprops/action-gh-release@v2
+          for binary in sif-linux-amd64 sif-linux-386 sif-linux-arm64; do
+            arch="${arch_map[$binary]}"
+            pkg_dir="sif_${{ env.VERSION }}_${arch}"
+
+            mkdir -p "${pkg_dir}/DEBIAN"
+            mkdir -p "${pkg_dir}/usr/bin"
+            mkdir -p "${pkg_dir}/usr/share/sif/modules"
+
+            cp "${binary}" "${pkg_dir}/usr/bin/sif"
+            chmod 755 "${pkg_dir}/usr/bin/sif"
+            cp -r modules/* "${pkg_dir}/usr/share/sif/modules/"
+
+            cat > "${pkg_dir}/DEBIAN/control" << EOF
+          Package: sif
+          Version: ${{ env.VERSION }}
+          Section: security
+          Priority: optional
+          Architecture: ${arch}
+          Maintainer: vmfunc <celeste@linux.com>
+          Homepage: https://github.com/vmfunc/sif
+          Description: Modular pentesting toolkit
+           sif is a fast, concurrent, and extensible pentesting toolkit written in Go.
+           It supports multiple scan types including directory fuzzing, subdomain
+           enumeration, port scanning, and vulnerability detection.
+          EOF
+
+            dpkg-deb --build "${pkg_dir}"
+          done
+
+      - name: generate checksums
+        run: |
+          sha256sum \
+            sif-windows-amd64.zip \
+            sif-windows-386.zip \
+            sif-macos-amd64.tar.gz \
+            sif-macos-arm64.tar.gz \
+            sif-linux-amd64.tar.gz \
+            sif-linux-386.tar.gz \
+            sif-linux-arm64.tar.gz \
+            sif_*.deb \
+            > checksums-sha256.txt
+
+      - name: generate SBOM
+        uses: anchore/sbom-action@v0
         with:
-          tag_name: automated-release-${{ env.RELEASE_VERSION }}
-          name: Release ${{ env.RELEASE_VERSION }}
+          artifact-name: sbom.spdx.json
+          output-file: sbom.spdx.json
+
+      - name: generate changelog
+        id: changelog
+        uses: actions/github-script@v9
+        with:
+          result-encoding: string
+          script: |
+            const { data: releases } = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              per_page: 1,
+            });
+
+            const prev = releases.length > 0 ? releases[0].tag_name : '';
+            const range = prev ? `${prev}...${context.ref}` : '';
+
+            const { data: commits } = await github.rest.repos.compareCommitsWithBasehead({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              basehead: prev ? `${prev}...${{ github.ref_name }}` : `${{ github.sha }}~10...${{ github.sha }}`,
+            }).catch(() => ({ data: { commits: [] } }));
+
+            let log = '';
+            for (const c of commits.commits || []) {
+              const msg = c.commit.message.split('\n')[0];
+              const sha = c.sha.substring(0, 7);
+              log += `- ${msg} (${sha})\n`;
+            }
+
+            return log || 'initial release';
+
+      - name: create release
+        uses: softprops/action-gh-release@v3
+        with:
+          name: sif v${{ env.VERSION }}
           body: |
-            Automated release v${{ env.RELEASE_VERSION }}
+            ## what's changed
 
-            ## Assets
+            ${{ steps.changelog.outputs.result }}
 
-            Each archive contains the sif binary and built-in modules.
-
-            - Windows (64-bit): `sif-windows-amd64.zip`
-            - Windows (32-bit): `sif-windows-386.zip`
-            - macOS (64-bit Intel): `sif-macos-amd64.tar.gz`
-            - macOS (64-bit ARM): `sif-macos-arm64.tar.gz`
-            - Linux (64-bit): `sif-linux-amd64.tar.gz`
-            - Linux (32-bit): `sif-linux-386.tar.gz`
-            - Linux (64-bit ARM): `sif-linux-arm64.tar.gz`
-
-            ## Installation
+            ## install
 
+            **homebrew / linuxbrew**
             ```bash
-            tar -xzf sif-linux-amd64.tar.gz
-            cd sif-linux-amd64
-            ./sif -h
+            # coming soon
             ```
 
-            For more details, check the [commit history](https://github.com/${{ github.repository }}/commits/main).
+            **debian / ubuntu**
+            ```bash
+            sudo dpkg -i sif_${{ env.VERSION }}_amd64.deb
+            ```
+
+            **go install**
+            ```bash
+            go install github.com/dropalldatabases/sif/cmd/sif@v${{ env.VERSION }}
+            ```
+
+            **binary download** - grab the right archive from below.
+
+            ## verification
+
+            ```bash
+            sha256sum -c checksums-sha256.txt
+            ```
           draft: false
-          prerelease: false
+          prerelease: ${{ contains(github.ref_name, '-') }}
           files: |
             sif-windows-amd64.zip
             sif-windows-386.zip
@@ -97,5 +191,20 @@ jobs:
             sif-linux-amd64.tar.gz
             sif-linux-386.tar.gz
             sif-linux-arm64.tar.gz
+            sif_*_amd64.deb
+            sif_*_i386.deb
+            sif_*_arm64.deb
+            checksums-sha256.txt
+            sbom.spdx.json
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: push to cloudsmith
+        if: ${{ !contains(github.ref_name, '-') }}
+        env:
+          CLOUDSMITH_API_KEY: ${{ secrets.CLOUDSMITH_API_KEY }}
+        run: |
+          pip install cloudsmith-cli
+          for deb in sif_*.deb; do
+            cloudsmith push deb sif/deb/any-distro/any-version "$deb" -k "$CLOUDSMITH_API_KEY"
+          done

.github/workflows/reportcard.yml

@@ -1,4 +1,4 @@
-name: Update Report Card
+name: update report card
 
 on:
   push:
@@ -7,10 +7,17 @@ on:
     branches: [main]
   workflow_call:
 
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   update-report-card:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - name: Update Go Report Card
+      - uses: actions/checkout@v7
+      - name: update go report card
         uses: creekorful/goreportcard-action@v1.0

.github/workflows/runtest.yml

@@ -1,4 +1,4 @@
-name: Functional Test
+name: functional test
 
 on:
   push:
@@ -7,18 +7,21 @@ on:
     branches: [main]
   workflow_call:
 
+permissions:
+  contents: read
+
 jobs:
   build-and-test:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - name: Set up Go
-        uses: actions/setup-go@v4
+      - uses: actions/checkout@v7
+      - name: set up go
+        uses: actions/setup-go@v5
         with:
-          go-version: "1.24"
-      - name: Build Sif
+          go-version: "1.25"
+      - name: build sif
         run: make
-      - name: Run Sif with features
+      - name: run sif with features
         run: |
           ./sif -u https://example.com -dnslist small -dirlist small -dork -git -whois -cms -framework
           if [ $? -eq 0 ]; then
@@ -28,7 +31,7 @@ jobs:
             exit 1
           fi
 
-      - name: Test module system
+      - name: test module system
         run: |
           echo "Listing modules..."
           ./sif -lm

.github/workflows/scorecard.yml

@@ -0,0 +1,30 @@
+name: scorecard
+
+on:
+  push:
+    branches: [main]
+  schedule:
+    - cron: "0 6 * * 1" # monday 06:00 UTC
+
+permissions: read-all
+
+jobs:
+  analysis:
+    runs-on: ubuntu-latest
+    permissions:
+      security-events: write
+      id-token: write
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          persist-credentials: false
+      - name: run scorecard
+        uses: ossf/scorecard-action@v2.4.3
+        with:
+          results_file: results.sarif
+          results_format: sarif
+          publish_results: true
+      - name: upload sarif results
+        uses: github/codeql-action/upload-sarif@v4
+        with:
+          sarif_file: results.sarif

.github/workflows/shellcheck.yml

@@ -1,18 +1,22 @@
-name: Shell Check
+name: shell check
 
 on:
   pull_request:
     paths:
       - "**/*.sh"
 
+permissions:
+  contents: read
+  pull-requests: write
+
 jobs:
   shellcheck:
     name: runner / shellcheck
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
       - name: shellcheck
-        uses: reviewdog/action-shellcheck@v1.27.0
+        uses: reviewdog/action-shellcheck@v1.32.0
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           reporter: github-pr-review

.github/workflows/yaml-lint.yml

@@ -1,4 +1,4 @@
-name: YAML Lint
+name: yaml lint
 
 on:
   pull_request:
@@ -6,14 +6,18 @@ on:
       - "**/*.yml"
       - "**/*.yaml"
 
+permissions:
+  contents: read
+  pull-requests: write
+
 jobs:
   yamllint:
     name: runner / yamllint
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
       - name: yamllint
-        uses: reviewdog/action-yamllint@v1.19.0
+        uses: reviewdog/action-yamllint@v1.21.0
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           reporter: github-pr-review

.golangci.yml

@@ -1,39 +1,96 @@
-linters:
-  enable:
-    - errcheck      # check error returns
-    - govet         # suspicious constructs
-    - staticcheck   # advanced static analysis
-    - unused        # unused code
-    - gosimple      # simplifications
-    - ineffassign   # useless assignments
-    - misspell      # spelling mistakes
-    - gocritic      # opinionated lints
-    - revive        # replacement for golint
-    - unconvert     # unnecessary type conversions
-    - prealloc      # slice preallocation hints
-    - bodyclose     # http response body not closed
-    - noctx         # http requests without context
-    - exportloopref # loop variable capture
-
-linters-settings:
-  govet:
-    enable-all: true
-  errcheck:
-    check-blank: false
-  revive:
-    rules:
-      - name: exported
-        arguments: [checkPrivateReceivers]
-  gocritic:
-    enabled-tags:
-      - diagnostic
-      - style
-      - performance
+---
+version: "2"
 
 run:
   timeout: 5m
   issues-exit-code: 1
 
+linters:
+  enable:
+    - errcheck      # check error returns
+    - govet         # suspicious constructs
+    - staticcheck   # advanced static analysis (absorbs gosimple in v2)
+    - unused        # unused code
+    - ineffassign   # useless assignments
+    - misspell      # spelling mistakes
+    - gocritic      # opinionated lints
+    - revive        # replacement for golint
+    - unconvert     # unnecessary type conversions
+    - bodyclose     # http response body not closed
+    - noctx         # http requests without context
+    - gosec         # security issues
+    - errorlint     # error wrapping and comparison
+    - nilnil        # return nil, nil
+    - wastedassign  # assignments to variables never read
+    - usetesting    # os.Setenv in tests instead of t.Setenv, etc.
+
+  settings:
+    govet:
+      enable-all: true
+      disable:
+        # too many structs to reorder, risks breaking serialization
+        - fieldalignment
+        - shadow          # common Go pattern, too noisy
+        - unusedwrite     # false positives on test data structs
+    errcheck:
+      check-blank: false
+      exclude-functions:
+        # log writes are best-effort
+        - github.com/dropalldatabases/sif/internal/logger.Write
+        # Close on io.Closer is idiomatic best-effort
+        - (io.Closer).Close
+        - (*os.File).Close
+        - (*net/http.Response).Body.Close
+        # fmt.Fprint* returns are rarely actionable
+        - fmt.Fprint
+        - fmt.Fprintf
+        - fmt.Fprintln
+    staticcheck:
+      # QF1003/QF1012 are v2 quickfix suggestions, not bugs.
+      # ST1000/ST1003 were the stylecheck linter in v1
+      # (not previously enabled); skipping to match prior parity.
+      checks:
+        - all
+        - -QF1003
+        - -QF1012
+        - -ST1000
+        - -ST1003
+    revive:
+      rules:
+        # stuttering names (scan.ScanResult) need breaking API changes
+        - name: exported
+          disabled: true
+    gocritic:
+      enabled-tags:
+        - diagnostic
+        - style
+        - performance
+      disabled-checks:
+        - commentedOutCode   # too opinionated for a project with TODOs
+        - paramTypeCombine   # style-only, not worth churn
+        - unnamedResult      # style-only
+        - unnecessaryDefer   # common pattern in tests
+        # inverting conditions in scan logic hurts readability
+        - nestingReduce
+    gosec:
+      excludes:
+        - G104  # errcheck covers this
+        - G107  # pentesting tool -- variable URLs are the whole point
+        - G110  # nuclei template decompression, acceptable context
+        - G304  # sif reads user-supplied wordlist paths -- intentional
+        - G305  # tar extraction is traversal-guarded (HasPrefix on the
+                # cleaned target); gosec flags filepath.Join regardless
+
+  exclusions:
+    rules:
+      # test files get some slack
+      - path: _test\.go
+        linters:
+          - errcheck
+          - noctx
+          - gosec  # fake credentials in secret-scanner fixtures are not real keys
+          - bodyclose  # synthetic *http.Response fixtures carry no socket to close
+
 issues:
   max-issues-per-linter: 50
-  max-same-issues: 3
+  max-same-issues: 50

CONTRIBUTING.md

@@ -4,17 +4,19 @@ Thank you for taking the time to contribute to sif! All contributions are valued
 If you want to contribute but don't know where to start, worry not; there is no shortage of things to do.  
 Even if you don't know any Go, don't let that stop you from trying to contribute! We're here to help.
 
-*By contributing to this repository, you agree to adhere to the sif [Code of Conduct](https://github.com/dropalldatabases/sif/blob/main/CODE_OF_CONDUCT.md). Not doing so may result in a ban.*
+_By contributing to this repository, you agree to adhere to the sif [Code of Conduct](https://github.com/vmfunc/sif/blob/main/CODE_OF_CONDUCT.md). Not doing so may result in a ban._
 
 ## How can I help?
 
 Here are some ways to get started:
-- Have a look at our [issue tracker](https://github.com/dropalldatabases/sif/issues).
+
+- Have a look at our [issue tracker](https://github.com/vmfunc/sif/issues).
 - If you've encountered a bug, discuss it with us, [report it](#reporting-issues).
 - Once you've found a bug you believe you can fix, open a [pull request](#contributing-code) for it.
 - Alternatively, consider [packaging sif for your distribution](#packaging).
 
 If you like the project, but don't have time to contribute, that's okay too! Here are other ways to show your appreciation for the project:
+
 - Use sif (seriously, that's enough)
 - Star the repository
 - Share sif with your friends
@@ -22,7 +24,7 @@ If you like the project, but don't have time to contribute, that's okay too! Her
 
 ## Reporting issues
 
-If you believe you've found a bug, or you have a new feature to request, please hop on the [Discord server](https://discord.gg/dropalldatabases) first to discuss it.  
+If you believe you've found a bug, or you have a new feature to request, please hop on the [Discord server](https://discord.com/invite/sifcli) first to discuss it.  
 This way, if it's an easy fix, we could help you solve it more quickly, and if it's a feature request we could workshop it together into something more mature.
 
 When opening an issue, please use the search tool and make sure that the issue has not been discussed before. In the case of a bug report, run sif with the `-d/-debug` flag for full debug logs.
@@ -31,9 +33,9 @@ When opening an issue, please use the search tool and make sure that the issue h
 
 ### Development
 
-To develop sif, you'll need version 1.23 or later of the Go toolchain. After making your changes, run the program using `go run ./cmd/sif` to make sure it compiles and runs properly.
+To develop sif, you'll need version 1.25 or later of the Go toolchain. After making your changes, run the program using `go run ./cmd/sif` to make sure it compiles and runs properly.
 
-*Nix users:* the repository provides a flake that can be used to develop and run sif. Use `nix run`, `nix develop`, `nix build`, etc. Make sure to run `gomod2nix` if `go.mod` is changed.
+_Nix users:_ the repository provides a flake that can be used to develop and run sif. Use `nix run`, `nix develop`, `nix build`, etc. Make sure to run `gomod2nix` if `go.mod` is changed.
 
 ### Submitting a pull request
 
@@ -55,21 +57,40 @@ If you have any questions, feel free to ask around on the IRC channel.
 
 ## Contributing Framework Detection Patterns
 
-The framework detection module (`pkg/scan/frameworks/detect.go`) identifies web frameworks by analyzing HTTP headers and response bodies. To add support for a new framework:
+The framework detection module (`internal/scan/frameworks/`) identifies web frameworks by analyzing HTTP headers and response bodies. Detectors are organized by category in the `detectors/` subdirectory:
 
-### Adding a New Framework Signature
+### Adding a New Framework Detector
 
-1. Add your framework to the `frameworkSignatures` map:
+1. Create a detector struct in the appropriate file in `detectors/`:
 
 ```go
-"MyFramework": {
-    {Pattern: `unique-identifier`, Weight: 0.5},
-    {Pattern: `header-signature`, Weight: 0.4, HeaderOnly: true},
-    {Pattern: `body-signature`, Weight: 0.3},
-},
+// myframeworkDetector detects MyFramework.
+type myframeworkDetector struct{}
+
+func (d *myframeworkDetector) Name() string { return "MyFramework" }
+
+func (d *myframeworkDetector) Signatures() []fw.Signature {
+    return []fw.Signature{
+        {Pattern: "unique-identifier", Weight: 0.5},
+        {Pattern: "header-signature", Weight: 0.4, HeaderOnly: true},
+        {Pattern: "body-signature", Weight: 0.3},
+    }
+}
+
+...
+
+```
+
+2. Register the detector in the `init()` function of the same file:
+
+```go
+func init() {
+    fw.Register(&myframeworkDetector{})
+}
 ```
 
 **Pattern Guidelines:**
+
 - `Weight`: How much this signature contributes to detection (0.0-1.0)
 - `HeaderOnly`: Set to `true` for HTTP header patterns
 - Use unique identifiers that won't false-positive on other frameworks
@@ -77,10 +98,11 @@ The framework detection module (`pkg/scan/frameworks/detect.go`) identifies web
 
 ### Adding Version Detection
 
-Add version patterns to `extractVersionWithConfidence()`:
+Add version patterns to `version.go` in the `rawPatterns` map inside `init()`:
 
 ```go
 "MyFramework": {
+    {`<meta name="generator" content="MyFramework v?(\d+\.\d+(?:\.\d+)?)"`, 0.95, "generator meta"},
     {`MyFramework[/\s]+[Vv]?(\d+\.\d+(?:\.\d+)?)`, 0.9, "explicit version"},
     {`"myframework":\s*"[~^]?(\d+\.\d+(?:\.\d+)?)"`, 0.85, "package.json"},
 },
@@ -88,7 +110,7 @@ Add version patterns to `extractVersionWithConfidence()`:
 
 ### Adding CVE Data
 
-Add known vulnerabilities to the `knownCVEs` map:
+Add known vulnerabilities to `cve.go` in the `knownCVEs` map:
 
 ```go
 "MyFramework": {
@@ -115,11 +137,17 @@ func TestDetectFramework_MyFramework(t *testing.T) {
     }))
     defer server.Close()
 
-    result, err := DetectFramework(server.URL, 5*time.Second, "")
+    result, err := frameworks.DetectFramework(server.URL, 5*time.Second, "")
     // assertions...
 }
 ```
 
+Also add your framework to the registry test in `TestDetectorRegistry`:
+
+```go
+expectedDetectors := []string{"Laravel", "Django", ..., "MyFramework"}
+```
+
 ### Future Enhancements (Help Wanted)
 
 - **Custom Signature Support**: Allow users to define signatures via config file
@@ -131,18 +159,18 @@ func TestDetectFramework_MyFramework(t *testing.T) {
 
 ### Framework Detection Flags
 
-| Flag | Description |
-|------|-------------|
-| `-framework` | Enable framework detection |
-| `-timeout` | HTTP request timeout (affects all modules) |
-| `-threads` | Number of concurrent workers |
-| `-log` | Directory to save scan results |
-| `-debug` | Enable debug logging for verbose output |
+| Flag         | Description                                |
+| ------------ | ------------------------------------------ |
+| `-framework` | Enable framework detection                 |
+| `-timeout`   | HTTP request timeout (affects all modules) |
+| `-threads`   | Number of concurrent workers               |
+| `-log`       | Directory to save scan results             |
+| `-debug`     | Enable debug logging for verbose output    |
 
 ### Environment Variables
 
-| Variable | Description |
-|----------|-------------|
+| Variable         | Description                          |
+| ---------------- | ------------------------------------ |
 | `SHODAN_API_KEY` | API key for Shodan host intelligence |
 
 ## Packaging

LICENSE

@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) 2022-2025 vmfunc (vmfunc), xyzeva, lunchcat alumni,
+Copyright (c) 2022-2025 vmfunc, xyzeva, lunchcat alumni,
 and other sif contributors.
 
 Redistribution and use in source and binary forms, with or without

Makefile

@@ -9,6 +9,12 @@ RM ?= rm
 GOFLAGS ?=
 PREFIX ?= /usr/local
 BINDIR ?= bin
+MANDIR ?= share/man/man1
+
+# stamp local builds with the nearest v* tag (or short sha), matching the
+# release ci. --match keeps the automated-release-* tags out of the version.
+VERSION ?= $(shell git describe --tags --match 'v*' --always --dirty 2>/dev/null | sed 's/^v//')
+GO_LDFLAGS = -X main.version=$(VERSION)
 
 define COPYRIGHT_ASCII
 ╭────────────────────────────────────────────────────────────╮
@@ -32,8 +38,7 @@ define SUPPORT_MESSAGE
 │                                                            │
 │  🌟 Enjoying sif? Please consider:                         │
 │                                                            │
-│  • Starring our repo: https://github.com/lunchcat/sif      │
-│  • Supporting the devs: https://lunchcat.dev               │
+│  • Starring our repo: https://github.com/vmfunc/sif        │
 │                                                            │
 │  Your support helps us continue improving sif!             │
 │                                                            │
@@ -56,7 +61,7 @@ sif: check_go_version
 	@echo "📁 Current directory: $$(pwd)"
 	@echo "🔧 Go flags: $(GOFLAGS)"
 	@echo "📦 Building package: ./cmd/sif"
-	$(GO) build -v $(GOFLAGS) ./cmd/sif
+	$(GO) build -v $(GOFLAGS) -ldflags "$(GO_LDFLAGS)" ./cmd/sif
 	@echo "📊 Build info:"
 	@$(GO) version -m sif
 	@echo "✅ sif built successfully! 🚀"
@@ -76,6 +81,9 @@ install: check_go_version
 	fi
 	@mkdir -p $(DESTDIR)$(PREFIX)/$(BINDIR) || (echo "🔒 Permission denied. Trying with sudo..." && sudo mkdir -p $(DESTDIR)$(PREFIX)/$(BINDIR))
 	@cp -f sif $(DESTDIR)$(PREFIX)/$(BINDIR) || (echo "🔒 Permission denied. Trying with sudo..." && sudo cp -f sif $(DESTDIR)$(PREFIX)/$(BINDIR))
+	@echo "📖 Installing man page..."
+	@mkdir -p $(DESTDIR)$(PREFIX)/$(MANDIR) || (echo "🔒 Permission denied. Trying with sudo..." && sudo mkdir -p $(DESTDIR)$(PREFIX)/$(MANDIR))
+	@cp -f man/sif.1 $(DESTDIR)$(PREFIX)/$(MANDIR) || (echo "🔒 Permission denied. Trying with sudo..." && sudo cp -f man/sif.1 $(DESTDIR)$(PREFIX)/$(MANDIR))
 	@echo "✅ sif installed successfully! 🎊"
 
 uninstall:
@@ -86,6 +94,7 @@ uninstall:
 		exit 1; \
 	fi
 	@$(RM) $(DESTDIR)$(PREFIX)/$(BINDIR)/sif || (echo "🔒 Permission denied. Trying with sudo..." && sudo $(RM) $(DESTDIR)$(PREFIX)/$(BINDIR)/sif)
+	@$(RM) $(DESTDIR)$(PREFIX)/$(MANDIR)/sif.1 || (echo "🔒 Permission denied. Trying with sudo..." && sudo $(RM) $(DESTDIR)$(PREFIX)/$(MANDIR)/sif.1)
 	@echo "✅ sif uninstalled successfully!"
 
 .PHONY: all check_go_version sif clean install uninstall

README.md

@@ -8,23 +8,39 @@
 [![build](https://img.shields.io/github/actions/workflow/status/vmfunc/sif/go.yml?style=flat-square)](https://github.com/vmfunc/sif/actions)
 [![license](https://img.shields.io/badge/license-BSD--3--Clause-blue?style=flat-square)](LICENSE)
 [![aur](https://img.shields.io/aur/version/sif?style=flat-square&logo=archlinux&logoColor=white&color=1793D1)](https://aur.archlinux.org/packages/sif)
+[![nixpkgs](https://img.shields.io/badge/nixpkgs-sif-5277C3?style=flat-square&logo=nixos&logoColor=white)](https://search.nixos.org/packages?query=sif)
 [![homebrew](https://img.shields.io/badge/homebrew-tap-FBB040?style=flat-square&logo=homebrew&logoColor=white)](https://github.com/vmfunc/homebrew-sif)
-[![discord](https://img.shields.io/badge/discord-join-5865F2?style=flat-square&logo=discord&logoColor=white)](https://discord.gg/sifcli)
+[![apt](https://img.shields.io/badge/apt-cloudsmith-2A5ADF?style=flat-square&logo=debian&logoColor=white)](https://cloudsmith.io/~sif/repos/deb/packages/)
+[![discord](https://img.shields.io/badge/discord-join-5865F2?style=flat-square&logo=discord&logoColor=white)](https://discord.gg/Yksy9J2BvE)
 
 **[install](#install) · [usage](#usage) · [modules](#modules) · [docs](docs/) · [contribute](#contribute)**
 
+*fast, concurrent recon to exploitation in one binary. every scanner shares one connection-pooled http client.*
+
 </div>
 
 ---
 
 ## what is sif?
 
-sif is a modular pentesting toolkit written in go. it's designed to be fast, concurrent, and extensible. run multiple scan types against targets with a single command.
+sif is a recon and exploitation scanner that runs the whole chain in one binary: subdomain enum, port scan, crawler, nuclei, framework/cve detection, js secret extraction, web-vuln probes (cors/xss/redirect), cloud and takeover checks. 25+ scan types, one command.
 
 ```bash
-./sif -u https://example.com -all
+sif -u https://example.com -dnslist -ports -crawl -js -framework -nuclei
 ```
 
+nuclei and colly are compiled in as libraries rather than shelled out to (there's no `exec.Command` in the tree), so it's a single static binary with no runtime dependencies and nothing to wire together.
+
+every scanner runs through one shared http client and a work-stealing worker pool. `-proxy`, `-H`, `-cookie` and `-rate-limit` apply to the whole run at once, connections get pooled and reused across the scan (a single-host run reuses one connection for ~50 requests instead of dialing 50 times), and a slow host doesn't hold the rest up. that shared client is the practical reason to use it over piping a stack of separate tools together. port scanning is `connect()`-based, so rustscan and nmap are still faster at raw port scans.
+
+it reads targets from stdin and prints findings one per line under `-silent`, so it composes:
+
+```bash
+subfinder -d example.com | sif -silent -crawl -js -nuclei | notify
+```
+
+`-diff` turns a re-scan into a monitor that only reports what changed, `-notify` posts to slack/discord/telegram/webhook, and runs export to sarif and markdown.
+
 ## install
 
 ### homebrew (macos)
@@ -44,6 +60,32 @@ yay -S sif
 paru -S sif
 ```
 
+### nix
+
+```bash
+# nixpkgs (declarative: add to configuration.nix or home-manager)
+environment.systemPackages = [ pkgs.sif ];
+
+# or imperatively
+nix profile install nixpkgs#sif
+
+# or just run it without installing
+nix run nixpkgs#sif -- -u https://example.com -headers -sh -framework
+```
+
+the repo also ships a flake if you want to build from source:
+
+```bash
+nix run github:vmfunc/sif
+```
+
+### debian/ubuntu (apt)
+
+```bash
+curl -1sLf 'https://dl.cloudsmith.io/public/sif/deb/setup.deb.sh' | sudo -E bash
+sudo apt-get install sif
+```
+
 ### from releases
 
 grab the latest binary from [releases](https://github.com/vmfunc/sif/releases).
@@ -56,7 +98,7 @@ cd sif
 make
 ```
 
-requires go 1.23+
+requires go 1.25+
 
 ### aur (manual install)
 
@@ -87,18 +129,39 @@ makepkg -si
 # shodan host intelligence (requires SHODAN_API_KEY env var)
 ./sif -u https://example.com -shodan
 
+# securitytrails domain discovery (requires SECURITYTRAILS_API_KEY env var)
+# discovers subdomains + associated domains, then scans all of them
+./sif -u https://example.com -securitytrails -headers
+
 # sql recon + lfi scanning
 ./sif -u https://example.com -sql -lfi
 
+# web vuln probes (cors, open redirect, reflected xss)
+./sif -u https://example.com -cors -redirect -xss
+
 # framework detection (with cve lookup)
 ./sif -u https://example.com -framework
 
-# everything
-./sif -u https://example.com -all
+# a broad sweep
+./sif -u https://example.com -dirlist small -dnslist small -ports common -headers -sh -cms -framework -git -whois
 ```
 
 run `./sif -h` for all options.
 
+## commands
+
+a couple of subcommands run without scanning:
+
+```bash
+# print the version (release builds are stamped; local builds use git describe)
+./sif version
+
+# show the latest release notes (also -pn)
+./sif patchnote
+```
+
+the first time you run a new release, sif prints that release's notes once. set `SIF_NO_PATCHNOTES=1` to turn that off.
+
 ## modules
 
 sif has a modular architecture. modules are defined in yaml and can be extended by users.
@@ -108,21 +171,133 @@ sif has a modular architecture. modules are defined in yaml and can be extended
 | flag | description |
 |------|-------------|
 | `-dirlist` | directory and file fuzzing (small/medium/large) |
+| `-mc` | dirlist: match these status codes (comma list, e.g. 200,301) |
+| `-fc` | dirlist: filter out these status codes (comma list) |
+| `-fs` | dirlist: filter out responses of these body sizes (comma list) |
+| `-fw` | dirlist: filter out responses with these word counts (comma list) |
+| `-fr` | dirlist: filter out responses whose body matches this regex |
+| `-ac` | auto-calibrate the soft-404 wildcard baseline (dirlist, sql) |
+| `-w` | dirlist: custom wordlist (local file or url; overrides `-dirlist` size) |
+| `-e` | dirlist: extensions appended to each word (comma list, e.g. php,bak,env) |
 | `-dnslist` | subdomain enumeration (small/medium/large) |
 | `-ports` | port scanning (common/full) |
 | `-nuclei` | vulnerability scanning with nuclei templates |
 | `-dork` | automated google dorking |
-| `-js` | javascript analysis |
+| `-js` | javascript analysis + secret and endpoint extraction |
 | `-c3` | cloud storage misconfiguration |
 | `-headers` | http header analysis |
+| `-sh` | security header analysis (missing/weak headers) |
 | `-st` | subdomain takeover detection |
 | `-cms` | cms detection |
 | `-whois` | whois lookups |
 | `-git` | exposed git repository detection |
 | `-shodan` | shodan lookup (requires SHODAN_API_KEY) |
+| `-securitytrails` | domain discovery + target expansion (requires SECURITYTRAILS_API_KEY) |
 | `-sql` | sql recon |
 | `-lfi` | local file inclusion |
+| `-jwt` | jwt discovery + offline weakness analysis (alg:none, weak hmac, exp, sensitive claims) |
+| `-openapi` | openapi/swagger spec exposure probe (enumerates paths + unauth endpoints) |
+| `-favicon` | favicon hash fingerprinting (shodan-style mmh3, tech match + pivot query) |
+| `-cors` | cors misconfiguration probe |
+| `-redirect` | open redirect probe |
+| `-xss` | reflected xss probe |
 | `-framework` | framework detection with cve lookup |
+| `-crawl` | web crawler (spider same-host links/scripts/forms) |
+| `-crawl-depth` | max crawl recursion depth (default 2) |
+| `-passive` | passive subdomain/url discovery (zero traffic to target) |
+| `-probe` | live-host probe (status, title, server, redirect chain) |
+
+### http options
+
+these apply to every outbound request across all scanners:
+
+| flag | description |
+|------|-------------|
+| `-proxy` | route all traffic through a proxy (http/https/socks5 url) |
+| `-H`, `--header` | custom header to send (repeatable or comma-separated, `"Key: Value"`) |
+| `-cookie` | cookie header to send with every request |
+| `-rate-limit` | max requests per second (0 = unlimited, default 0) |
+
+```bash
+# scan through a socks5 proxy with a custom header, cookie and 20 req/s cap
+./sif -u https://example.com -headers -proxy socks5://127.0.0.1:1080 -H "Authorization: Bearer tok" -cookie "session=abc" -rate-limit 20
+```
+
+a scanner that sets a header explicitly (e.g. an api key) always wins over the global default.
+
+### report export
+
+write the run's findings out to a file for ci/cd or triage:
+
+| flag | description |
+|------|-------------|
+| `-sarif` | write a sarif 2.1.0 report to this file |
+| `-markdown`, `-md` | write a markdown report to this file |
+| `-silent` | plain output: chrome to stderr, one finding per line to stdout (for pipelines) |
+| `-diff` | surface only findings added/removed since the last snapshot of each target |
+| `-store` | snapshot directory for `-diff` (default: log dir, else `<user-config>/sif/state`) |
+
+```bash
+# scan and emit both a sarif and markdown report
+./sif -u https://example.com -headers -cors -sarif out.sarif -md out.md
+```
+
+sarif output is ingestable by github code scanning; markdown is a readable per-target summary.
+
+### diff mode
+
+`-diff` turns a re-scan into a monitor: sif snapshots each target's normalized findings to a json file, and on the next run reports only the delta (`+ new` / `- gone`) against that snapshot, then overwrites it. the first run for a target has no baseline, so everything is `+ new`. snapshots land in `-store` (one sanitized file per target); when unset they reuse the log dir, falling back to `<user-config>/sif/state`.
+
+```bash
+# baseline run, then re-scan later and see only what moved
+./sif -u https://example.com -sh -cors -diff
+./sif -u https://example.com -sh -cors -diff
+```
+
+the snapshot is always rewritten, so each run diffs against the previous one. the delta is chrome (it rides the normal output sink / stderr under `-silent`), not the findings stream.
+
+### notify
+
+ship findings to a chat/webhook sink so a continuous-recon run alerts on what it turns up. every provider is a single POST through the shared http client, so the global proxy/rate-limit/header config applies.
+
+| flag | description |
+|------|-------------|
+| `-notify` | ship findings to every configured provider after the scan |
+| `-notify-severity` | minimum severity to send (`info`/`low`/`medium`/`high`/`critical`, default `medium`) |
+| `-notify-config` | path to a notify-compatible yaml config (overrides env vars) |
+
+providers are configured env-first; a yaml file (`-notify-config`) overrides per-field. the yaml keys match [projectdiscovery/notify](https://github.com/projectdiscovery/notify) so an existing config ports over:
+
+| env var | yaml key | provider |
+|---------|----------|----------|
+| `SLACK_WEBHOOK_URL` | `slack_webhook_url` | slack incoming webhook |
+| `DISCORD_WEBHOOK_URL` | `discord_webhook_url` | discord webhook |
+| `TELEGRAM_BOT_TOKEN` | `telegram_api_key` | telegram bot api (needs chat id too) |
+| `TELEGRAM_CHAT_ID` | `telegram_chat_id` | telegram destination chat |
+| `NOTIFY_WEBHOOK_URL` | `webhook_url` | generic json webhook (structured findings) |
+
+```bash
+# alert slack on medium+ findings discovered during a scan
+export SLACK_WEBHOOK_URL=https://hooks.slack.com/services/...
+./sif -u https://example.com -cors -xss -notify -notify-severity medium
+```
+
+a provider with no destination is skipped; with nothing configured, `-notify` is a silent no-op. slack/discord/telegram receive a fixed-width finding block; the generic webhook receives structured json (`{count, findings[]}`).
+
+### pipe mode
+
+sif reads targets from stdin and accepts naked hosts, so it drops into a unix pipeline. `-silent` routes all banner/spinner/log chrome to stderr and prints one normalized finding per line (`[severity] target module title`) to stdout:
+
+```bash
+# subfinder feeds hosts, sif probes them, notify ships the findings
+subfinder -d example.com | sif -silent -probe | notify
+```
+
+| flag | description |
+|------|-------------|
+| stdin | a piped target stream (one host/url per line) is read alongside `-u`/`-f` |
+
+scheme-less hosts default to `https://`; an explicit `http://`/`https://` is kept; any other scheme (`ftp://`, ...) is rejected.
 
 ### yaml modules
 
@@ -190,7 +365,7 @@ contributions welcome. see [contributing.md](CONTRIBUTING.md) for guidelines.
 gofmt -w .
 
 # lint
-golangci-lint run
+go run github.com/golangci/golangci-lint/v2/cmd/golangci-lint@v2.11.4 run
 
 # test
 go test ./...
@@ -210,13 +385,13 @@ join our discord for support, feature discussions, and pentesting tips:
 <table>
   <tbody>
     <tr>
-      <td align="center" valign="top" width="14.28%"><a href="https://vmfunc.re"><img src="https://avatars.githubusercontent.com/u/59031302?v=4?s=100" width="100px;" alt="vmfunc"/><br /><sub><b>vmfunc</b></sub></a><br /><a href="#maintenance-vmfunc" title="Maintenance">🚧</a> <a href="#mentoring-vmfunc" title="Mentoring">🧑‍🏫</a> <a href="#projectManagement-vmfunc" title="Project Management">📆</a> <a href="#security-vmfunc" title="Security">🛡️</a> <a href="https://github.com/lunchcat/sif/commits?author=vmfunc" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://vmfunc.re"><img src="https://avatars.githubusercontent.com/u/59031302?v=4?s=100" width="100px;" alt="vmfunc"/><br /><sub><b>vmfunc</b></sub></a><br /><a href="#maintenance-vmfunc" title="Maintenance">🚧</a> <a href="#mentoring-vmfunc" title="Mentoring">🧑‍🏫</a> <a href="#projectManagement-vmfunc" title="Project Management">📆</a> <a href="#security-vmfunc" title="Security">🛡️</a> <a href="https://github.com/vmfunc/sif/commits?author=vmfunc" title="Code">💻</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://projectdiscovery.io"><img src="https://avatars.githubusercontent.com/u/50994705?v=4?s=100" width="100px;" alt="ProjectDiscovery"/><br /><sub><b>ProjectDiscovery</b></sub></a><br /><a href="#platform-projectdiscovery" title="Packaging/porting to new platform">📦</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/macdoos"><img src="https://avatars.githubusercontent.com/u/127897805?v=4?s=100" width="100px;" alt="macdoos"/><br /><sub><b>macdoos</b></sub></a><br /><a href="https://github.com/lunchcat/sif/commits?author=macdoos" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/macdoos"><img src="https://avatars.githubusercontent.com/u/127897805?v=4?s=100" width="100px;" alt="macdoos"/><br /><sub><b>macdoos</b></sub></a><br /><a href="https://github.com/vmfunc/sif/commits?author=macdoos" title="Code">💻</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://epitech.eu"><img src="https://avatars.githubusercontent.com/u/75166283?v=4?s=100" width="100px;" alt="Matthieu Witrowiez"/><br /><sub><b>Matthieu Witrowiez</b></sub></a><br /><a href="#ideas-D3adPlays" title="Ideas, Planning, & Feedback">🤔</a></td>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/tessa-u-k"><img src="https://avatars.githubusercontent.com/u/109355732?v=4?s=100" width="100px;" alt="tessa "/><br /><sub><b>tessa </b></sub></a><br /><a href="#infra-tessa-u-k" title="Infrastructure (Hosting, Build-Tools, etc)">🚇</a> <a href="#question-tessa-u-k" title="Answering Questions">💬</a> <a href="#userTesting-tessa-u-k" title="User Testing">📓</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/xyzeva"><img src="https://avatars.githubusercontent.com/u/133499694?v=4?s=100" width="100px;" alt="Eva"/><br /><sub><b>Eva</b></sub></a><br /><a href="#blog-xyzeva" title="Blogposts">📝</a> <a href="#content-xyzeva" title="Content">🖋</a> <a href="#research-xyzeva" title="Research">🔬</a> <a href="#security-xyzeva" title="Security">🛡️</a> <a href="https://github.com/lunchcat/sif/commits?author=xyzeva" title="Tests">⚠️</a> <a href="https://github.com/lunchcat/sif/commits?author=xyzeva" title="Code">💻</a></td>
-      <td align="center" valign="top" width="14.28%"><a href="https://github.com/vxfemboy"><img src="https://avatars.githubusercontent.com/u/79362520?v=4?s=100" width="100px;" alt="Zoa Hickenlooper"/><br /><sub><b>Zoa Hickenlooper</b></sub></a><br /><a href="https://github.com/lunchcat/sif/commits?author=vxfemboy" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/xyzeva"><img src="https://avatars.githubusercontent.com/u/133499694?v=4?s=100" width="100px;" alt="Eva"/><br /><sub><b>Eva</b></sub></a><br /><a href="#blog-xyzeva" title="Blogposts">📝</a> <a href="#content-xyzeva" title="Content">🖋</a> <a href="#research-xyzeva" title="Research">🔬</a> <a href="#security-xyzeva" title="Security">🛡️</a> <a href="https://github.com/vmfunc/sif/commits?author=xyzeva" title="Tests">⚠️</a> <a href="https://github.com/vmfunc/sif/commits?author=xyzeva" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/vxfemboy"><img src="https://avatars.githubusercontent.com/u/79362520?v=4?s=100" width="100px;" alt="Zoa Hickenlooper"/><br /><sub><b>Zoa Hickenlooper</b></sub></a><br /><a href="https://github.com/vmfunc/sif/commits?author=vxfemboy" title="Code">💻</a></td>
     </tr>
     <tr>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/0xatrilla"><img src="https://avatars.githubusercontent.com/u/107285362?v=4?s=100" width="100px;" alt="acxtrilla"/><br /><sub><b>acxtrilla</b></sub></a><br /><a href="#platform-0xatrilla" title="Packaging/porting to new platform">📦</a></td>

SECURITY.md

@@ -0,0 +1,15 @@
+# security policy
+
+## reporting a vulnerability
+
+if you find a security issue in sif, email celeste@linux.com directly.
+don't open a public issue.
+
+expect a response within 48 hours. if it's confirmed, i'll push a fix
+and credit you in the release notes (unless you'd rather stay anonymous).
+
+## scope
+
+sif is a pentesting tool — "it can scan things" is not a vulnerability.
+actual bugs: command injection in user input handling, path traversal in
+template extraction, credential leaks, that kind of thing.

cmd/sif/main.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
@@ -13,15 +13,38 @@
 package main
 
 import (
+	"fmt"
+	"os"
+
 	"github.com/charmbracelet/log"
 	"github.com/dropalldatabases/sif"
 	"github.com/dropalldatabases/sif/internal/config"
+	"github.com/dropalldatabases/sif/internal/patchnotes"
+	ver "github.com/dropalldatabases/sif/internal/version"
 
 	// Register framework detectors
 	_ "github.com/dropalldatabases/sif/internal/scan/frameworks/detectors"
 )
 
+// version is stamped at release time via -ldflags "-X main.version=...";
+// ver.Resolve falls back to the build info or "dev" for other builds.
+var version = "dev"
+
 func main() {
+	version = ver.Resolve(version)
+	sif.Version = version
+
+	if len(os.Args) > 1 {
+		switch os.Args[1] {
+		case "patchnote", "patchnotes", "-pn", "--patchnotes":
+			patchnotes.Print("")
+			return
+		case "version", "-version", "--version":
+			fmt.Printf("sif %s\n", version)
+			return
+		}
+	}
+
 	settings := config.Parse()
 
 	app, err := sif.New(settings)
@@ -29,6 +52,12 @@ func main() {
 		log.Fatal(err)
 	}
 
+	// patchnotes print to stdout; skip them in api/silent mode so the only thing
+	// on stdout is the machine-readable result stream.
+	if !settings.ApiMode && !settings.Silent {
+		patchnotes.ShowOnce(version)
+	}
+
 	err = app.Run()
 	if err != nil {
 		log.Fatal(err)

docs/configuration.md

@@ -57,6 +57,12 @@ enable verbose logging:
 ./sif -u https://example.com -d
 ```
 
+### templates
+
+`-template` loads a batch of scan settings from a built-in preset or a local yaml file, so a run does not have to pass every flag. see the [usage guide](usage.md) for the presets and file format. command-line flags still take precedence over the template.
+
+sif also reads an ambient config at `~/.config/sif/config.yaml` (created on first run) keyed by the same flag names. passing `-template` uses that template as the config for the run instead of the ambient file.
+
 ## user modules
 
 place custom modules in:
@@ -92,6 +98,38 @@ info:
   # ...
 ```
 
+## custom signatures
+
+framework detection (`-framework`) also loads user-defined detectors from yaml
+files, so a framework sif does not ship can be detected without rebuilding:
+
+- linux/macos: `~/.config/sif/signatures/`
+- windows: `%LOCALAPPDATA%\sif\signatures\`
+
+each file defines one detector; place them directly in the directory, as
+subdirectories are not scanned. `header: true` matches a response header name or
+value (case-insensitive) instead of the body; the optional `version` block pulls
+a version out of the body.
+
+```yaml
+# ~/.config/sif/signatures/ghost.yaml
+name: Ghost
+signatures:
+  - pattern: 'content="Ghost'
+    weight: 0.6
+  - pattern: 'X-Ghost-Cache'
+    weight: 0.4
+    header: true
+version:
+  regex: 'content="Ghost ([0-9.]+)'
+  group: 1
+```
+
+a detector reports a match once its matched signature weights sum past half, so
+weight your signatures to total about `1.0`. a name matching a built-in detector
+overrides it and inherits that built-in's version patterns and known cves, the
+same as user modules.
+
 ## performance tuning
 
 ### fast scans

docs/development.md

@@ -4,7 +4,7 @@ setting up a development environment for sif.
 
 ## prerequisites
 
-- go 1.23 or later
+- go 1.25 or later
 - git
 - make
 
@@ -28,8 +28,7 @@ sif/
 │   ├── logger/       # logging utilities
 │   ├── modules/      # module system
 │   ├── scan/         # built-in scans
-│   ├── styles/       # terminal styling
-│   └── worker/       # worker pool
+│   └── styles/       # terminal styling
 ├── modules/          # built-in yaml modules
 │   ├── http/         # http-based modules
 │   ├── info/         # information gathering
@@ -61,8 +60,11 @@ gofmt -w .
 
 ### lint
 
+ci pins golangci-lint v2.11.4 (`.github/workflows/go.yml`); other versions
+report spurious issues against the v2 config, so pin it locally too:
+
 ```bash
-golangci-lint run
+go run github.com/golangci/golangci-lint/v2/cmd/golangci-lint@v2.11.4 run
 ```
 
 ### test
@@ -138,6 +140,15 @@ the module system is in `internal/modules/`:
 go test ./internal/...
 ```
 
+### integration tests
+
+run the scanners against a local testbed that plants the artifacts each one
+should find (network-free, behind a build tag):
+
+```bash
+go test -tags=integration ./internal/scan/...
+```
+
 ### functional test
 
 ```bash
@@ -156,7 +167,7 @@ go test ./internal/...
 1. fork the repository
 2. create a feature branch
 3. make changes
-4. run `gofmt -w .` and `golangci-lint run`
+4. run `gofmt -w .` and `golangci-lint run` (pinned version, see [lint](#lint))
 5. submit pr
 
 ### commit messages

docs/installation.md

@@ -36,7 +36,7 @@ download `sif-windows-amd64.exe` from releases and add to your PATH.
 
 ## from source
 
-requires go 1.23+
+requires go 1.25+
 
 ```bash
 git clone https://github.com/dropalldatabases/sif.git

docs/modules.md

@@ -115,6 +115,29 @@ http:
 
 each payload creates a separate request for each path.
 
+#### attack
+
+how paths and payloads combine into requests.
+
+```yaml
+http:
+  attack: pitchfork
+```
+
+- `clusterbomb` (default) - every path is tried with every payload
+- `pitchfork` - path and payload are paired by index, stopping at the shorter list
+
+#### wordlist
+
+a local file whose non-empty lines fuzz the `{{word}}` placeholder, one request
+per word. paths without `{{word}}` are still requested as-is.
+
+```yaml
+http:
+  wordlist: /usr/share/wordlists/dirs.txt
+  paths:
+    - "{{BaseURL}}/{{word}}"
+```
 #### headers
 
 custom headers to send.
@@ -199,6 +222,42 @@ matchers:
     condition: or
 ```
 
+### size matcher
+
+match the response body length in bytes (measured after the 5 MB response cap, so larger sizes never match).
+
+```yaml
+matchers:
+  - type: size
+    size:
+      - 0
+      - 1337
+```
+
+### favicon matcher
+
+match the shodan-style mmh3 hash of the response body. point the module at a
+favicon and list the hashes of the tech you want to fingerprint.
+
+```yaml
+http:
+  paths:
+    - "{{BaseURL}}/favicon.ico"
+  matchers:
+    - type: status
+      status:
+        - 200
+    - type: favicon
+      hash:
+        - -235701012   # jenkins
+        - 1278322581   # grafana
+```
+
+the hash is shodan's `http.favicon.hash` value. paste it signed or unsigned;
+both 32-bit forms are accepted, so values from shodan or any favicon-hash tool
+drop in without conversion. pair it with a `status: 200` matcher so an error
+page served for `/favicon.ico` is not hashed. a finding fires when the body
+hashes to any listed value.
 ### combining matchers
 
 multiple matchers are combined with AND logic by default.
@@ -218,6 +277,25 @@ matchers:
 
 this matches responses with status 200 AND containing "ref: refs/".
 
+to require any matcher instead of all, set `matchers-condition: or` on the http
+block; the module then reports a finding when any one matcher matches.
+
+```yaml
+http:
+  matchers-condition: or
+  matchers:
+    - type: status
+      status:
+        - 401
+
+    - type: status
+      status:
+        - 403
+```
+
+this matches a 401 OR a 403 response. `matchers-condition` accepts `and` (the
+default) or `or`; any other value fails at load.
+
 ## extractors
 
 extractors pull data from responses.
@@ -238,7 +316,7 @@ extractors:
 
 ### kv extractor
 
-extract key-value pairs.
+record every response header as a key-value pair, namespaced by `name`.
 
 ```yaml
 extractors:
@@ -247,6 +325,21 @@ extractors:
     part: header
 ```
 
+### json extractor
+
+extract values from a json body by gjson path (github.com/tidwall/gjson); the
+first path that exists is stored under name.
+
+```yaml
+extractors:
+  - type: json
+    name: version
+    part: body
+    json:
+      - "version"
+      - "data.version"
+```
+
 ## examples
 
 ### exposed git repository

docs/scans.md

@@ -98,16 +98,27 @@ analyzes javascript files for security issues.
 
 ## http headers (-headers)
 
-analyzes security headers.
+dumps the target's response headers.
+
+## security headers (-sh)
+
+flags missing or weak security headers and headers that leak server internals.
 
 ### checks
 
+- strict-transport-security (https only)
 - content-security-policy
 - x-frame-options
-- x-content-type-options
-- strict-transport-security
-- x-xss-protection
+- x-content-type-options (expects nosniff)
+- referrer-policy
 - permissions-policy
+- cross-origin-opener-policy
+
+### flagged as disclosure
+
+- server
+- x-powered-by
+- x-aspnet-version / x-aspnetmvc-version
 
 ## cms detection (-cms)
 

docs/usage.md

@@ -21,6 +21,23 @@ read targets from a file (one url per line):
 ./sif -f targets.txt
 ```
 
+### stdin (pipe mode)
+
+when stdin is a pipe, sif reads one target per line from it, alongside any `-u`/`-f` targets. this lets sif slot into a unix pipeline:
+
+```bash
+subfinder -d example.com | sif -silent -probe | notify
+```
+
+### naked hosts
+
+targets without a scheme default to `https://`; an explicit `http://`/`https://` is kept as given. any other scheme (`ftp://`, `file://`, ...) is rejected:
+
+```bash
+./sif -u example.com          # scanned as https://example.com
+echo example.com | sif -probe # same, over stdin
+```
+
 ## scan options
 
 ### directory fuzzing
@@ -33,6 +50,42 @@ sizes: `small`, `medium`, `large`
 ./sif -u https://example.com -dirlist medium
 ```
 
+#### response filters
+
+modern apps serve a catch-all 200 for unknown routes, so a naive scan reports
+every path. these ffuf-style filters cut the noise (a filter always wins over a
+match):
+
+- `-mc <codes>` - match only these status codes (comma list, e.g. `200,301`)
+- `-fc <codes>` - filter out these status codes
+- `-fs <sizes>` - filter out responses of these body sizes
+- `-fw <counts>` - filter out responses with these word counts
+- `-fr <regex>` - filter out responses whose body matches this regex
+
+```bash
+./sif -u https://example.com -dirlist medium -mc 200,301 -fs 1234
+```
+
+#### wildcard calibration
+
+`-ac` probes a few paths that cannot exist, learns the soft-404 baseline
+(status + size + words), and auto-drops any response matching it - so SPA
+catch-all 200s stop flooding the output:
+
+```bash
+./sif -u https://example.com -dirlist medium -ac
+```
+
+#### custom wordlists and extensions
+
+`-w <path|url>` overrides the size switch with your own list (local file or
+remote url); `-e <exts>` appends each extension to every word, keeping the bare
+word too:
+
+```bash
+./sif -u https://example.com -w /path/to/words.txt -e php,bak,env
+```
+
 ### subdomain enumeration
 
 `-dnslist <size>` - enumerate subdomains
@@ -79,7 +132,7 @@ scopes: `common` (top ports), `full` (all ports)
 
 ### javascript analysis
 
-`-js` - analyze javascript files
+`-js` - analyze javascript files + secret and endpoint extraction
 
 ```bash
 ./sif -u https://example.com -js
@@ -95,12 +148,20 @@ scopes: `common` (top ports), `full` (all ports)
 
 ### http headers
 
-`-headers` - analyze security headers
+`-headers` - dump the target's response headers
 
 ```bash
 ./sif -u https://example.com -headers
 ```
 
+### security headers
+
+`-sh` - flag missing/weak security headers (hsts, csp, x-frame-options, ...) and headers that leak server internals
+
+```bash
+./sif -u https://example.com -sh
+```
+
 ### cloud storage
 
 `-c3` - check for cloud storage misconfigurations
@@ -146,6 +207,56 @@ export SHODAN_API_KEY=your-api-key
 ./sif -u https://example.com -lfi
 ```
 
+### cors probe
+
+`-cors` - probe for cors misconfigurations (reflected/permissive origins)
+
+```bash
+./sif -u https://example.com -cors
+```
+
+### open redirect probe
+
+`-redirect` - probe redirect-prone params for open redirects
+
+```bash
+./sif -u https://example.com/login?next=home -redirect
+```
+
+### reflected xss probe
+
+`-xss` - inject a canary into params and report unescaped reflections
+
+```bash
+./sif -u https://example.com/search?q=test -xss
+```
+
+### jwt analysis
+
+`-jwt` - fetch the target once, harvest jwts from response headers, cookies and body, then analyze each one entirely offline
+
+flags alg:none, the rs256->hs256 confusion surface, missing/expired exp, plaintext sensitive claims, and cracks a small bundled weak-hmac wordlist. no token is ever sent off-box.
+
+```bash
+./sif -u https://example.com -jwt
+```
+
+### openapi/swagger exposure
+
+`-openapi` - probe the conventional spec paths (`/swagger.json`, `/openapi.json`, `/v3/api-docs`, ...), parse the first hit (json or yaml) and enumerate every path+method, flagging operations with no security requirement
+
+```bash
+./sif -u https://example.com -openapi
+```
+
+### favicon fingerprint
+
+`-favicon` - fetch `/favicon.ico` (or the declared `<link rel=icon>`), compute the shodan-style mmh3 hash, match it against a bundled tech map and print the `http.favicon.hash:<n>` pivot query
+
+```bash
+./sif -u https://example.com -favicon
+```
+
 ### framework detection
 
 `-framework` - detect web frameworks with version and cve lookup
@@ -154,6 +265,34 @@ export SHODAN_API_KEY=your-api-key
 ./sif -u https://example.com -framework
 ```
 
+### web crawler
+
+`-crawl` - spider the target, following same-host links, scripts and forms
+
+`-crawl-depth` - max recursion depth (default 2). respects robots.txt and stays on the target host.
+
+```bash
+./sif -u https://example.com -crawl -crawl-depth 3
+```
+
+### passive discovery
+
+`-passive` - gather subdomains from certificate transparency (crt.sh, certspotter) and historical urls from the wayback machine
+
+keyless and zero traffic to the target itself - all lookups hit third-party feeds.
+
+```bash
+./sif -u https://example.com -passive
+```
+
+### live-host probe
+
+`-probe` - check whether the target is alive and report its final status, page title, server header, content-length and the redirect chain it walked
+
+```bash
+./sif -u https://example.com -probe
+```
+
 ### whois lookup
 
 `-whois` - perform whois lookups
@@ -217,7 +356,7 @@ http request timeout (default: 10s):
 
 ### --threads
 
-number of concurrent threads (default: 10):
+number of concurrent threads (default: 10). values below 1 are clamped to 1:
 
 ```bash
 ./sif -u https://example.com --threads 20
@@ -239,6 +378,169 @@ enable debug logging:
 ./sif -u https://example.com -d
 ```
 
+### --template
+
+load a batch of scan settings from a template instead of passing each flag. the value is either a built-in preset or a local yaml file keyed by flag long-names:
+
+```bash
+./sif -u https://example.com --template recon
+./sif -u https://example.com --template ./my-scans.yaml
+```
+
+built-in presets:
+
+- `minimal`: liveness and fingerprint only (probe, headers, favicon)
+- `recon`: broad non-intrusive discovery, no attack payloads
+- `full`: every scan except the api-key ones (shodan, securitytrails), including the intrusive probes (xss, sql, lfi, redirect)
+
+`full` sends attack payloads, so only run it against targets you are authorized to test.
+
+a local template lists flag long-names, for example:
+
+```yaml
+cms: true
+dirlist: medium
+threads: 20
+```
+
+flags passed on the command line take precedence over the template, so `--template recon -xss` runs the recon preset with an added xss probe.
+
+## http options
+
+these apply to every outbound request across all scanners (proxy, custom headers, cookie and rate limiting share one client). a scanner that sets a header explicitly still wins over the global default.
+
+### -proxy
+
+route all traffic through a proxy. supports http, https and socks5 urls:
+
+```bash
+./sif -u https://example.com -proxy socks5://127.0.0.1:1080
+```
+
+### -H, --header
+
+add a custom header to every request. repeatable or comma-separated, `"Key: Value"`:
+
+```bash
+./sif -u https://example.com -H "Authorization: Bearer tok" -H "X-Env: staging"
+```
+
+### -cookie
+
+cookie header to send with every request:
+
+```bash
+./sif -u https://example.com -cookie "session=abc; theme=dark"
+```
+
+### -rate-limit
+
+cap outbound requests per second (0 = unlimited, default 0):
+
+```bash
+./sif -u https://example.com -rate-limit 20
+```
+
+## output options
+
+write the collected findings out to a file after the scan. both formats can be requested in the same run.
+
+### -sarif
+
+write a sarif 2.1.0 report (one run, tool `sif`, one result per finding). ingestable by github code scanning and other sarif consumers:
+
+```bash
+./sif -u https://example.com -headers -cors -sarif out.sarif
+```
+
+### -md, --markdown
+
+write a readable markdown report grouped by target, then by module:
+
+```bash
+./sif -u https://example.com -headers -cors -md report.md
+```
+
+### -silent
+
+plain output for pipelines: all banner/spinner/log chrome goes to stderr and stdout carries one normalized finding per line, formatted `[severity] target module title`. implies non-interactive (no spinners), so a downstream consumer sees nothing but findings:
+
+```bash
+subfinder -d example.com | sif -silent -probe -sh | notify
+```
+
+### -diff
+
+turn a re-scan into a monitor. sif snapshots each target's normalized findings to a json file under the store dir; on the next run it loads that snapshot, diffs the current findings against it by finding key, and prints only the delta (`+ new` for findings that appeared, `- gone` for findings that vanished). it always rewrites the snapshot afterwards, so each run compares against the previous one.
+
+the first run for a target has no snapshot, so every finding shows as `+ new`. when nothing changed, sif notes that and writes a fresh snapshot anyway.
+
+```bash
+# baseline, then re-scan and see only what moved
+./sif -u https://example.com -sh -cors -diff
+./sif -u https://example.com -sh -cors -diff
+```
+
+the delta is chrome, not the findings stream: under `-silent` it rides stderr with the rest of the chrome, leaving stdout for the full findings.
+
+### -store
+
+snapshot directory for `-diff`. precedence when unset: the `-log` dir if one is given, else `<user-config>/sif/state` (`$XDG_CONFIG_HOME/sif/state` on linux, `~/Library/Application Support/sif/state` on macos). one sanitized file per target, created at `0750`, written `0600`.
+
+```bash
+./sif -u https://example.com -sh -diff -store ./snapshots
+```
+
+
+## notify options
+
+ship findings to a chat/webhook sink after the scan. every provider is a single POST through the shared http client, so the global proxy/rate-limit/header config applies. with nothing configured, `-notify` is a silent no-op.
+
+### -notify
+
+enable delivery to every configured provider:
+
+```bash
+export SLACK_WEBHOOK_URL=https://hooks.slack.com/services/...
+./sif -u https://example.com -cors -xss -notify
+```
+
+### -notify-severity
+
+minimum severity to send: `info`, `low`, `medium`, `high` or `critical` (default `medium`). findings below the floor are dropped, so info-level recon noise doesn't flood a channel. an unrecognized value falls back to `medium`:
+
+```bash
+./sif -u https://example.com -cors -notify -notify-severity high
+```
+
+### -notify-config
+
+path to a yaml config that overrides the env vars per-field. the keys match [projectdiscovery/notify](https://github.com/projectdiscovery/notify) so an existing config ports over:
+
+```yaml
+slack_webhook_url: https://hooks.slack.com/services/...
+discord_webhook_url: https://discord.com/api/webhooks/...
+telegram_api_key: 123456:abcdef
+telegram_chat_id: "987654"
+webhook_url: https://example.internal/sif-findings
+```
+
+```bash
+./sif -u https://example.com -cors -notify -notify-config notify.yaml
+```
+
+providers are resolved env-first, then overlaid by the yaml file:
+
+| env var | yaml key | provider |
+|---------|----------|----------|
+| `SLACK_WEBHOOK_URL` | `slack_webhook_url` | slack incoming webhook |
+| `DISCORD_WEBHOOK_URL` | `discord_webhook_url` | discord webhook |
+| `TELEGRAM_BOT_TOKEN` | `telegram_api_key` | telegram bot api (needs chat id too) |
+| `TELEGRAM_CHAT_ID` | `telegram_chat_id` | telegram destination chat |
+| `NOTIFY_WEBHOOK_URL` | `webhook_url` | generic json webhook (structured findings) |
+
+slack/discord/telegram receive a fixed-width finding block; the generic webhook receives structured json (`{count, findings[]}`) for downstream automation.
+
 ## api options
 
 ### -api
@@ -251,6 +553,28 @@ enable api mode for json output:
 
 output is a json object with scan results.
 
+## commands
+
+these run without scanning a target.
+
+### version
+
+print the sif version. release builds are stamped via ldflags, local `make` builds derive it from `git describe`, and `go install`ed builds read it from the module build info:
+
+```bash
+./sif version
+```
+
+### patchnote
+
+show the latest release's notes, fetched from github (also `-pn`):
+
+```bash
+./sif patchnote
+```
+
+the first time you run a new release sif also prints that release's notes once. set `SIF_NO_PATCHNOTES=1` to disable that.
+
 ## examples
 
 ### quick recon
@@ -273,6 +597,9 @@ output is a json object with scan results.
   -git \
   -sql \
   -lfi \
+  -cors \
+  -redirect \
+  -xss \
   -am
 ```
 

flake.lock

@@ -2,11 +2,11 @@
   "nodes": {
     "nixpkgs": {
       "locked": {
-        "lastModified": 1767364772,
-        "narHash": "sha256-fFUnEYMla8b7UKjijLnMe+oVFOz6HjijGGNS1l7dYaQ=",
+        "lastModified": 1780930886,
+        "narHash": "sha256-rppURzHviaQN131F+nLiLdGfcb0uCd9gGP0E5+iw9MI=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "16c7794d0a28b5a37904d55bcca36003b9109aaa",
+        "rev": "8c3cede7ddc26bd659d2d383b5610efbd2c7a16e",
         "type": "github"
       },
       "original": {

flake.nix

@@ -21,7 +21,7 @@
             version = "unstable-${self.shortRev or self.dirtyShortRev or "dev"}";
             src = ./.;
 
-            vendorHash = "sha256-ztKXnOjZS/jMxsRjtF0rIZ3lKv4YjMdZd6oQFRuAtR4=";
+            vendorHash = "sha256-fR63/dStMsZon22vancuLWIAvZiEYMLjMwY1kmRDNgM=";
 
             # Tests require network access (httptest)
             doCheck = false;

go.mod

@@ -1,223 +1,408 @@
 module github.com/dropalldatabases/sif
 
-go 1.24.0
+go 1.25.7
 
 require (
-	github.com/antchfx/htmlquery v1.3.0
-	github.com/charmbracelet/lipgloss v0.8.0
-	github.com/charmbracelet/log v0.2.4
-	github.com/likexian/whois v1.15.1
-	github.com/projectdiscovery/goflags v0.1.54
-	github.com/projectdiscovery/nuclei/v2 v2.9.14
-	github.com/projectdiscovery/ratelimit v0.0.9
-	github.com/projectdiscovery/utils v0.1.1
+	github.com/antchfx/htmlquery v1.3.6
+	github.com/charmbracelet/glamour v1.0.0
+	github.com/charmbracelet/lipgloss v1.1.1-0.20250404203927-76690c660834
+	github.com/charmbracelet/log v1.0.0
+	github.com/gocolly/colly/v2 v2.3.0
+	github.com/likexian/whois v1.15.7
+	github.com/projectdiscovery/goflags v0.1.74
+	github.com/projectdiscovery/nuclei/v3 v3.9.0
+	github.com/projectdiscovery/retryabledns v1.0.115
+	github.com/projectdiscovery/utils v0.11.1
 	github.com/rocketlaunchr/google-search v1.1.6
+	github.com/tidwall/gjson v1.18.0
+	github.com/twmb/murmur3 v1.1.8
+	golang.org/x/net v0.56.0
+	golang.org/x/time v0.15.0
 	gopkg.in/yaml.v3 v3.0.1
 )
 
 require (
-	aead.dev/minisign v0.2.0 // indirect
+	aead.dev/minisign v0.3.0 // indirect
+	carvel.dev/ytt v0.52.0 // indirect
+	code.gitea.io/sdk/gitea v0.17.0 // indirect
+	dario.cat/mergo v1.0.2 // indirect
+	filippo.io/edwards25519 v1.1.1 // indirect
 	git.mills.io/prologic/smtpd v0.0.0-20210710122116-a525b76c287a // indirect
-	github.com/Knetic/govaluate v3.0.1-0.20171022003610-9aa49832a739+incompatible // indirect
-	github.com/Masterminds/semver/v3 v3.2.1 // indirect
+	github.com/Azure/azure-sdk-for-go/sdk/azcore v1.18.0 // indirect
+	github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.10.1 // indirect
+	github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.1 // indirect
+	github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v1.1.0 // indirect
+	github.com/Azure/go-ntlmssp v0.1.1 // indirect
+	github.com/AzureAD/microsoft-authentication-library-for-go v1.4.2 // indirect
+	github.com/FalconOpsLLC/goexec v0.3.0 // indirect
+	github.com/Masterminds/semver/v3 v3.4.0 // indirect
+	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/Mzack9999/gcache v0.0.0-20230410081825-519e28eab057 // indirect
 	github.com/Mzack9999/go-http-digest-auth-client v0.6.1-0.20220414142836-eb8883508809 // indirect
-	github.com/PuerkitoBio/goquery v1.8.1 // indirect
+	github.com/Mzack9999/go-rsync v0.0.0-20250821180103-81ffa574ef4d // indirect
+	github.com/Mzack9999/goimpacket v0.0.0-20260422121140-7085336a0415 // indirect
+	github.com/Mzack9999/goja v0.0.0-20250507184235-e46100e9c697 // indirect
+	github.com/Mzack9999/goja_nodejs v0.0.0-20250507184139-66bcbf65c883 // indirect
+	github.com/ProtonMail/go-crypto v1.1.6 // indirect
+	github.com/PuerkitoBio/goquery v1.11.0 // indirect
+	github.com/RedTeamPentesting/adauth v0.5.4-0.20260511073005-3d18e8a5a687 // indirect
+	github.com/STARRY-S/zip v0.2.3 // indirect
 	github.com/VividCortex/ewma v1.2.0 // indirect
-	github.com/akrylysov/pogreb v0.10.1 // indirect
+	github.com/akrylysov/pogreb v0.10.2 // indirect
 	github.com/alecthomas/chroma v0.10.0 // indirect
-	github.com/alecthomas/jsonschema v0.0.0-20211022214203-8b29eab41725 // indirect
+	github.com/alecthomas/chroma/v2 v2.20.0 // indirect
 	github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 // indirect
 	github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 // indirect
-	github.com/andybalholm/brotli v1.0.6 // indirect
-	github.com/andybalholm/cascadia v1.3.2 // indirect
-	github.com/andygrunwald/go-jira v1.16.0 // indirect
-	github.com/antchfx/xmlquery v1.3.15 // indirect
-	github.com/antchfx/xpath v1.2.4 // indirect
+	github.com/alexsnet/go-vnc v0.1.0 // indirect
+	github.com/alitto/pond v1.9.2 // indirect
+	github.com/andybalholm/brotli v1.2.0 // indirect
+	github.com/andybalholm/cascadia v1.3.3 // indirect
+	github.com/andygrunwald/go-jira v1.16.1 // indirect
+	github.com/antchfx/xmlquery v1.5.0 // indirect
+	github.com/antchfx/xpath v1.3.6 // indirect
 	github.com/asaskevich/govalidator v0.0.0-20230301143203-a9d515a09cc2 // indirect
-	github.com/aws/aws-sdk-go-v2 v1.19.0 // indirect
-	github.com/aws/aws-sdk-go-v2/config v1.18.28 // indirect
-	github.com/aws/aws-sdk-go-v2/credentials v1.13.27 // indirect
-	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.13.5 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/configsources v1.1.35 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.4.29 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/ini v1.3.36 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.9.29 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.12.13 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.14.13 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sts v1.19.3 // indirect
-	github.com/aws/smithy-go v1.13.5 // indirect
+	github.com/aws/aws-sdk-go-v2 v1.41.5 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8 // indirect
+	github.com/aws/aws-sdk-go-v2/config v1.29.17 // indirect
+	github.com/aws/aws-sdk-go-v2/credentials v1.17.70 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.32 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/s3/manager v1.17.82 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.21 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.3 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21 // indirect
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.99.0 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.25.5 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.30.3 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.34.0 // indirect
+	github.com/aws/smithy-go v1.24.2 // indirect
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
 	github.com/aymerick/douceur v0.2.0 // indirect
+	github.com/bahlo/generic-list-go v0.2.0 // indirect
+	github.com/bits-and-blooms/bitset v1.24.4 // indirect
+	github.com/bits-and-blooms/bloom/v3 v3.5.0 // indirect
 	github.com/bluele/gcache v0.0.2 // indirect
-	github.com/caddyserver/certmagic v0.19.2 // indirect
-	github.com/charmbracelet/glamour v0.6.0 // indirect
-	github.com/cheggaaa/pb/v3 v3.1.4 // indirect
+	github.com/bodgit/plumbing v1.3.0 // indirect
+	github.com/bodgit/sevenzip v1.6.1 // indirect
+	github.com/bodgit/windows v1.0.1 // indirect
+	github.com/brianvoe/gofakeit/v7 v7.2.1 // indirect
+	github.com/buger/jsonparser v1.1.2 // indirect
+	github.com/bytedance/gopkg v0.1.3 // indirect
+	github.com/bytedance/sonic v1.15.0 // indirect
+	github.com/bytedance/sonic/loader v0.5.0 // indirect
+	github.com/caddyserver/certmagic v0.25.0 // indirect
+	github.com/caddyserver/zerossl v0.1.3 // indirect
+	github.com/censys/censys-sdk-go v0.19.1 // indirect
+	github.com/cespare/xxhash v1.1.0 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
+	github.com/charmbracelet/colorprofile v0.3.2 // indirect
+	github.com/charmbracelet/x/ansi v0.10.2 // indirect
+	github.com/charmbracelet/x/cellbuf v0.0.13 // indirect
+	github.com/charmbracelet/x/exp/slice v0.0.0-20250908092851-c2208eb08494 // indirect
+	github.com/charmbracelet/x/term v0.2.1 // indirect
+	github.com/cheggaaa/pb/v3 v3.1.7 // indirect
+	github.com/clbanning/mxj/v2 v2.7.0 // indirect
 	github.com/cloudflare/cfssl v1.6.4 // indirect
-	github.com/cnf/structhash v0.0.0-20201127153200-e1b16c1ebc08 // indirect
-	github.com/corpix/uarand v0.2.0 // indirect
+	github.com/cloudflare/circl v1.6.3 // indirect
+	github.com/cloudwego/base64x v0.1.6 // indirect
+	github.com/cnf/structhash v0.0.0-20250313080605-df4c6cc74a9a // indirect
+	github.com/containerd/errdefs v1.0.0 // indirect
+	github.com/containerd/errdefs/pkg v0.3.0 // indirect
+	github.com/cyphar/filepath-securejoin v0.6.1 // indirect
+	github.com/davidmz/go-pageant v1.0.2 // indirect
+	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dimchansky/utfbom v1.1.1 // indirect
-	github.com/dlclark/regexp2 v1.8.1 // indirect
+	github.com/distribution/reference v0.6.0 // indirect
+	github.com/ditashi/jsbeautifier-go v0.0.0-20141206144643-2520a8026a9c // indirect
+	github.com/djherbis/times v1.6.0 // indirect
+	github.com/dlclark/regexp2 v1.11.5 // indirect
+	github.com/docker/go-connections v0.7.0 // indirect
 	github.com/docker/go-units v0.5.0 // indirect
-	github.com/dsnet/compress v0.0.2-0.20210315054119-f66993602bf5 // indirect
-	github.com/fatih/color v1.16.0 // indirect
+	github.com/dsnet/compress v0.0.2-0.20230904184137-39efe44ab707 // indirect
+	github.com/dustin/go-humanize v1.0.1 // indirect
+	github.com/ebitengine/purego v0.10.0 // indirect
+	github.com/emirpasic/gods v1.18.1 // indirect
+	github.com/ericlagergren/decimal v0.0.0-20240411145413-00de7ca16731 // indirect
+	github.com/fatih/color v1.18.0 // indirect
 	github.com/fatih/structs v1.1.0 // indirect
-	github.com/gabriel-vasile/mimetype v1.4.2 // indirect
-	github.com/go-logfmt/logfmt v0.6.0 // indirect
-	github.com/go-ole/go-ole v1.2.6 // indirect
+	github.com/felixge/fgprof v0.9.5 // indirect
+	github.com/felixge/httpsnoop v1.0.4 // indirect
+	github.com/free5gc/util v1.0.5-0.20230511064842-2e120956883b // indirect
+	github.com/gabriel-vasile/mimetype v1.4.8 // indirect
+	github.com/gaissmai/bart v0.28.0 // indirect
+	github.com/geoffgarside/ber v1.2.0 // indirect
+	github.com/getkin/kin-openapi v0.132.0 // indirect
+	github.com/gin-contrib/sse v0.1.0 // indirect
+	github.com/gin-gonic/gin v1.9.1 // indirect
+	github.com/go-asn1-ber/asn1-ber v1.5.8-0.20250403174932-29230038a667 // indirect
+	github.com/go-fed/httpsig v1.1.0 // indirect
+	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
+	github.com/go-git/go-billy/v5 v5.9.0 // indirect
+	github.com/go-git/go-git/v5 v5.19.1 // indirect
+	github.com/go-ldap/ldap/v3 v3.4.12 // indirect
+	github.com/go-logfmt/logfmt v0.6.1 // indirect
+	github.com/go-logr/logr v1.4.3 // indirect
+	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/go-ole/go-ole v1.3.0 // indirect
+	github.com/go-openapi/jsonpointer v0.21.0 // indirect
+	github.com/go-openapi/swag v0.23.0 // indirect
+	github.com/go-pdf/fpdf v0.9.0 // indirect
+	github.com/go-pg/pg/v10 v10.15.0 // indirect
+	github.com/go-pg/zerochecker v0.2.0 // indirect
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
-	github.com/go-playground/validator/v10 v10.14.1 // indirect
-	github.com/go-rod/rod v0.114.0 // indirect
+	github.com/go-playground/validator/v10 v10.26.0 // indirect
+	github.com/go-rod/rod v0.116.2 // indirect
+	github.com/go-sourcemap/sourcemap v2.1.4+incompatible // indirect
+	github.com/go-sql-driver/mysql v1.9.3 // indirect
 	github.com/goburrow/cache v0.1.4 // indirect
 	github.com/gobwas/glob v0.2.3 // indirect
 	github.com/gobwas/httphead v0.1.0 // indirect
 	github.com/gobwas/pool v0.2.1 // indirect
-	github.com/gobwas/ws v1.2.1 // indirect
-	github.com/gocolly/colly/v2 v2.1.0 // indirect
+	github.com/gobwas/ws v1.4.0 // indirect
+	github.com/goccy/go-json v0.10.5 // indirect
 	github.com/golang-jwt/jwt/v4 v4.5.2 // indirect
-	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
-	github.com/golang/protobuf v1.5.3 // indirect
-	github.com/golang/snappy v0.0.4 // indirect
-	github.com/google/certificate-transparency-go v1.1.4 // indirect
+	github.com/golang-jwt/jwt/v5 v5.2.2 // indirect
+	github.com/golang-sql/civil v0.0.0-20220223132316-b832511892a9 // indirect
+	github.com/golang-sql/sqlexp v0.1.0 // indirect
+	github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
+	github.com/golang/protobuf v1.5.4 // indirect
+	github.com/golang/snappy v1.0.0 // indirect
+	github.com/google/certificate-transparency-go v1.3.2 // indirect
 	github.com/google/go-github v17.0.0+incompatible // indirect
 	github.com/google/go-github/v30 v30.1.0 // indirect
 	github.com/google/go-querystring v1.1.0 // indirect
+	github.com/google/pprof v0.0.0-20240727154555-813a5fbdbec8 // indirect
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
-	github.com/google/uuid v1.3.1 // indirect
-	github.com/gorilla/css v1.0.0 // indirect
+	github.com/google/uuid v1.6.0 // indirect
+	github.com/gorilla/css v1.0.1 // indirect
+	github.com/gosimple/slug v1.15.0 // indirect
+	github.com/gosimple/unidecode v1.0.1 // indirect
 	github.com/h2non/filetype v1.1.3 // indirect
 	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
-	github.com/hashicorp/go-retryablehttp v0.7.7 // indirect
-	github.com/hashicorp/go-version v1.6.0 // indirect
+	github.com/hashicorp/go-retryablehttp v0.7.8 // indirect
+	github.com/hashicorp/go-uuid v1.0.3 // indirect
+	github.com/hashicorp/go-version v1.8.0 // indirect
+	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
 	github.com/hbakhtiyor/strsim v0.0.0-20190107154042-4d2bbb273edf // indirect
 	github.com/hdm/jarm-go v0.0.7 // indirect
-	github.com/iancoleman/orderedmap v0.0.0-20190318233801-ac98e3ecb4b0 // indirect
-	github.com/itchyny/gojq v0.12.13 // indirect
-	github.com/itchyny/timefmt-go v0.1.5 // indirect
+	github.com/iangcarroll/cookiemonster v1.6.0 // indirect
+	github.com/imdario/mergo v0.3.16 // indirect
+	github.com/indece-official/go-ebcdic v1.2.0 // indirect
+	github.com/invopop/jsonschema v0.13.0 // indirect
+	github.com/invopop/yaml v0.3.1 // indirect
+	github.com/itchyny/gojq v0.12.17 // indirect
+	github.com/itchyny/timefmt-go v0.1.6 // indirect
+	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
+	github.com/jcmturner/aescts/v2 v2.0.0 // indirect
+	github.com/jcmturner/dnsutils/v2 v2.0.0 // indirect
+	github.com/jcmturner/gofork v1.7.6 // indirect
+	github.com/jcmturner/goidentity/v6 v6.0.1 // indirect
+	github.com/jcmturner/gokrb5/v8 v8.4.4 // indirect
+	github.com/jcmturner/rpc/v2 v2.0.3 // indirect
+	github.com/jinzhu/inflection v1.0.0 // indirect
+	github.com/josharian/intern v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/julienschmidt/httprouter v1.3.0 // indirect
-	github.com/kataras/jwt v0.1.8 // indirect
+	github.com/k14s/starlark-go v0.0.0-20200720175618-3a5c849cc368 // indirect
+	github.com/kaiakz/ubuffer v0.0.0-20200803053910-dd1083087166 // indirect
+	github.com/kataras/jwt v0.1.10 // indirect
 	github.com/kennygrant/sanitize v1.2.4 // indirect
-	github.com/klauspost/compress v1.17.4 // indirect
-	github.com/klauspost/cpuid/v2 v2.2.5 // indirect
-	github.com/klauspost/pgzip v1.2.5 // indirect
-	github.com/leodido/go-urn v1.2.4 // indirect
-	github.com/libdns/libdns v0.2.1 // indirect
+	github.com/kevinburke/ssh_config v1.2.0 // indirect
+	github.com/kitabisa/go-ci v1.0.3 // indirect
+	github.com/klauspost/compress v1.18.5 // indirect
+	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
+	github.com/klauspost/pgzip v1.2.6 // indirect
+	github.com/kylelemons/godebug v1.1.0 // indirect
+	github.com/labstack/echo/v4 v4.13.4 // indirect
+	github.com/labstack/gommon v0.4.2 // indirect
+	github.com/leodido/go-urn v1.4.0 // indirect
+	github.com/leslie-qiwa/flat v0.0.0-20230424180412-f9d1cf014baa // indirect
+	github.com/lib/pq v1.11.2 // indirect
+	github.com/libdns/libdns v1.1.1 // indirect
 	github.com/logrusorgru/aurora v2.0.3+incompatible // indirect
-	github.com/lor00x/goldap v0.0.0-20180618054307-a546dffdd1a3 // indirect
-	github.com/lucasb-eyer/go-colorful v1.2.0 // indirect
-	github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0 // indirect
-	github.com/mackerelio/go-osstat v0.2.4 // indirect
-	github.com/mattn/go-colorable v0.1.13 // indirect
-	github.com/mattn/go-isatty v0.0.20 // indirect
-	github.com/mattn/go-runewidth v0.0.14 // indirect
-	github.com/mholt/acmez v1.2.0 // indirect
-	github.com/mholt/archiver v3.1.1+incompatible // indirect
-	github.com/mholt/archiver/v3 v3.5.1 // indirect
-	github.com/microcosm-cc/bluemonday v1.0.25 // indirect
-	github.com/miekg/dns v1.1.56 // indirect
+	github.com/logrusorgru/aurora/v4 v4.0.0 // indirect
+	github.com/lor00x/goldap v0.0.0-20240304151906-8d785c64d1c8 // indirect
+	github.com/lucasb-eyer/go-colorful v1.3.0 // indirect
+	github.com/lufia/plan9stats v0.0.0-20250827001030-24949be3fa54 // indirect
+	github.com/mackerelio/go-osstat v0.2.6 // indirect
+	github.com/mailru/easyjson v0.7.7 // indirect
+	github.com/mattn/go-colorable v0.1.14 // indirect
+	github.com/mattn/go-isatty v0.0.22 // indirect
+	github.com/mattn/go-runewidth v0.0.17 // indirect
+	github.com/mattn/go-sqlite3 v1.14.28 // indirect
+	github.com/maypok86/otter/v2 v2.2.1 // indirect
+	github.com/mholt/acmez/v3 v3.1.3 // indirect
+	github.com/mholt/archives v0.1.5 // indirect
+	github.com/microcosm-cc/bluemonday v1.0.27 // indirect
+	github.com/microsoft/go-mssqldb v1.9.2 // indirect
+	github.com/miekg/dns v1.1.68 // indirect
+	github.com/mikelolasagasti/xz v1.0.1 // indirect
+	github.com/minio/minlz v1.0.1 // indirect
 	github.com/minio/selfupdate v0.6.1-0.20230907112617-f11e74f84ca7 // indirect
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
+	github.com/moby/docker-image-spec v1.3.1 // indirect
+	github.com/moby/moby/api v1.54.2 // indirect
+	github.com/moby/moby/client v0.4.1 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/mohae/deepcopy v0.0.0-20170929034955-c48cc78d4826 // indirect
+	github.com/montanaflynn/stats v0.7.1 // indirect
 	github.com/muesli/reflow v0.3.0 // indirect
-	github.com/muesli/termenv v0.15.2 // indirect
-	github.com/nwaples/rardecode v1.1.3 // indirect
-	github.com/olekukonko/tablewriter v0.0.5 // indirect
-	github.com/pierrec/lz4 v2.6.1+incompatible // indirect
-	github.com/pierrec/lz4/v4 v4.1.2 // indirect
+	github.com/muesli/termenv v0.16.0 // indirect
+	github.com/nlnwa/whatwg-url v0.6.2 // indirect
+	github.com/nwaples/rardecode/v2 v2.2.2 // indirect
+	github.com/oasdiff/yaml v0.0.0-20250309154309-f31be36b4037 // indirect
+	github.com/oasdiff/yaml3 v0.0.0-20250309153720-d2182401db90 // indirect
+	github.com/oiweiwei/go-msrpc v1.2.12 // indirect
+	github.com/oiweiwei/go-smb2.fork v1.0.0 // indirect
+	github.com/oiweiwei/gokrb5.fork/v9 v9.0.6 // indirect
+	github.com/olekukonko/errors v1.1.0 // indirect
+	github.com/olekukonko/ll v0.0.9 // indirect
+	github.com/olekukonko/tablewriter v1.0.8 // indirect
+	github.com/opencontainers/go-digest v1.0.0 // indirect
+	github.com/opencontainers/image-spec v1.1.1 // indirect
+	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
+	github.com/perimeterx/marshmallow v1.1.5 // indirect
+	github.com/pierrec/lz4/v4 v4.1.23 // indirect
+	github.com/pjbgf/sha1cd v0.6.0 // indirect
+	github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect
 	github.com/pkg/errors v0.9.1 // indirect
-	github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c // indirect
-	github.com/projectdiscovery/asnmap v1.1.0 // indirect
+	github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 // indirect
+	github.com/praetorian-inc/fingerprintx v1.1.15 // indirect
+	github.com/projectdiscovery/asnmap v1.1.1 // indirect
 	github.com/projectdiscovery/blackrock v0.0.1 // indirect
-	github.com/projectdiscovery/cdncheck v1.0.9 // indirect
-	github.com/projectdiscovery/clistats v0.0.19 // indirect
-	github.com/projectdiscovery/dsl v0.0.20 // indirect
-	github.com/projectdiscovery/fastdialer v0.1.1 // indirect
+	github.com/projectdiscovery/cdncheck v1.2.39 // indirect
+	github.com/projectdiscovery/clistats v0.1.4 // indirect
+	github.com/projectdiscovery/dsl v0.8.19 // indirect
+	github.com/projectdiscovery/fastdialer v0.5.10 // indirect
 	github.com/projectdiscovery/fasttemplate v0.0.2 // indirect
-	github.com/projectdiscovery/freeport v0.0.5 // indirect
-	github.com/projectdiscovery/gologger v1.1.12 // indirect
-	github.com/projectdiscovery/gostruct v0.0.1 // indirect
-	github.com/projectdiscovery/hmap v0.0.45 // indirect
-	github.com/projectdiscovery/httpx v1.3.4 // indirect
-	github.com/projectdiscovery/interactsh v1.2.0 // indirect
+	github.com/projectdiscovery/freeport v0.0.7 // indirect
+	github.com/projectdiscovery/gcache v0.0.0-20241015120333-12546c6e3f4c // indirect
+	github.com/projectdiscovery/go-smb2 v0.0.0-20240129202741-052cc450c6cb // indirect
+	github.com/projectdiscovery/gologger v1.1.70 // indirect
+	github.com/projectdiscovery/gostruct v0.0.2 // indirect
+	github.com/projectdiscovery/govaluate v0.0.0-20260504230327-80320480bb6e // indirect
+	github.com/projectdiscovery/gozero v0.1.1-0.20260530071156-fa1dad563d76 // indirect
+	github.com/projectdiscovery/hmap v0.0.101 // indirect
+	github.com/projectdiscovery/httpx v1.9.0 // indirect
+	github.com/projectdiscovery/interactsh v1.3.1 // indirect
 	github.com/projectdiscovery/ldapserver v1.0.2-0.20240219154113-dcc758ebc0cb // indirect
-	github.com/projectdiscovery/machineid v0.0.0-20240226150047-2e2c51e35983 // indirect
-	github.com/projectdiscovery/mapcidr v1.1.34 // indirect
-	github.com/projectdiscovery/networkpolicy v0.0.8 // indirect
-	github.com/projectdiscovery/rawhttp v0.1.18 // indirect
+	github.com/projectdiscovery/machineid v0.0.0-20250715113114-c77eb3567582 // indirect
+	github.com/projectdiscovery/mapcidr v1.1.97 // indirect
+	github.com/projectdiscovery/n3iwf v0.0.0-20230523120440-b8cd232ff1f5 // indirect
+	github.com/projectdiscovery/networkpolicy v0.1.40 // indirect
+	github.com/projectdiscovery/ratelimit v0.0.88 // indirect
+	github.com/projectdiscovery/rawhttp v0.1.90 // indirect
 	github.com/projectdiscovery/rdap v0.9.1-0.20221108103045-9865884d1917 // indirect
-	github.com/projectdiscovery/retryabledns v1.0.62 // indirect
-	github.com/projectdiscovery/retryablehttp-go v1.0.63 // indirect
-	github.com/projectdiscovery/sarif v0.0.1 // indirect
-	github.com/projectdiscovery/tlsx v1.1.4 // indirect
-	github.com/projectdiscovery/yamldoc-go v1.0.4 // indirect
-	github.com/refraction-networking/utls v1.8.1 // indirect
+	github.com/projectdiscovery/retryablehttp-go v1.3.14 // indirect
+	github.com/projectdiscovery/sarif v0.1.0 // indirect
+	github.com/projectdiscovery/tlsx v1.2.2 // indirect
+	github.com/projectdiscovery/uncover v1.2.1 // indirect
+	github.com/projectdiscovery/useragent v0.0.108 // indirect
+	github.com/projectdiscovery/wappalyzergo v0.2.84 // indirect
+	github.com/projectdiscovery/yamldoc-go v1.0.6 // indirect
+	github.com/redis/go-redis/v9 v9.11.0 // indirect
+	github.com/refraction-networking/utls v1.8.2 // indirect
 	github.com/remeh/sizedwaitgroup v1.0.0 // indirect
-	github.com/rivo/uniseg v0.4.4 // indirect
-	github.com/rogpeppe/go-internal v1.10.0 // indirect
-	github.com/rs/xid v1.5.0 // indirect
+	github.com/rivo/uniseg v0.4.7 // indirect
+	github.com/rs/xid v1.6.0 // indirect
+	github.com/rs/zerolog v1.34.0 // indirect
 	github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d // indirect
-	github.com/sashabaranov/go-openai v1.14.2 // indirect
+	github.com/sashabaranov/go-openai v1.37.0 // indirect
 	github.com/segmentio/ksuid v1.0.4 // indirect
-	github.com/shirou/gopsutil/v3 v3.23.7 // indirect
-	github.com/shoenig/go-m1cpu v0.1.6 // indirect
+	github.com/sergi/go-diff v1.3.2-0.20230802210424-5b0b94c5c0d3 // indirect
+	github.com/shirou/gopsutil v3.21.11+incompatible // indirect
+	github.com/shirou/gopsutil/v4 v4.26.3 // indirect
+	github.com/shurcooL/graphql v0.0.0-20230722043721-ed46e5a46466 // indirect
+	github.com/sijms/go-ora/v2 v2.9.0 // indirect
+	github.com/sirupsen/logrus v1.9.4 // indirect
+	github.com/skeema/knownhosts v1.3.1 // indirect
+	github.com/sorairolake/lzip-go v0.3.8 // indirect
 	github.com/spaolacci/murmur3 v1.1.0 // indirect
-	github.com/spf13/cast v1.5.1 // indirect
-	github.com/stretchr/testify v1.11.1 // indirect
+	github.com/spf13/afero v1.15.0 // indirect
+	github.com/spf13/cast v1.10.0 // indirect
+	github.com/spf13/pflag v1.0.10 // indirect
 	github.com/syndtr/goleveldb v1.0.0 // indirect
 	github.com/temoto/robotstxt v1.1.2 // indirect
-	github.com/tidwall/btree v1.6.0 // indirect
-	github.com/tidwall/buntdb v1.3.0 // indirect
-	github.com/tidwall/gjson v1.14.4 // indirect
+	github.com/tidwall/btree v1.8.1 // indirect
+	github.com/tidwall/buntdb v1.3.2 // indirect
 	github.com/tidwall/grect v0.1.4 // indirect
-	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/match v1.2.0 // indirect
 	github.com/tidwall/pretty v1.2.1 // indirect
 	github.com/tidwall/rtred v0.1.2 // indirect
 	github.com/tidwall/tinyqueue v0.1.1 // indirect
-	github.com/tklauser/go-sysconf v0.3.12 // indirect
-	github.com/tklauser/numcpus v0.6.1 // indirect
+	github.com/tim-ywliu/nested-logrus-formatter v1.3.2 // indirect
+	github.com/tklauser/go-sysconf v0.3.16 // indirect
+	github.com/tklauser/numcpus v0.11.0 // indirect
+	github.com/tmthrgd/go-hex v0.0.0-20190904060850-447a3041c3bc // indirect
 	github.com/trivago/tgo v1.0.7 // indirect
+	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
+	github.com/ugorji/go/codec v1.2.11 // indirect
 	github.com/ulikunitz/xz v0.5.15 // indirect
 	github.com/valyala/bytebufferpool v1.0.0 // indirect
 	github.com/valyala/fasttemplate v1.2.2 // indirect
-	github.com/weppos/publicsuffix-go v0.30.1-0.20230422193905-8fecedd899db // indirect
-	github.com/xanzy/go-gitlab v0.84.0 // indirect
-	github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 // indirect
-	github.com/yl2chen/cidranger v1.0.2 // indirect
+	github.com/vmihailenco/bufpool v0.1.11 // indirect
+	github.com/vmihailenco/msgpack/v5 v5.3.4 // indirect
+	github.com/vmihailenco/tagparser v0.1.2 // indirect
+	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
+	github.com/vulncheck-oss/go-exploit v1.51.0 // indirect
+	github.com/weppos/publicsuffix-go v0.50.3 // indirect
+	github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect
+	github.com/xanzy/ssh-agent v0.3.3 // indirect
+	github.com/xdg-go/pbkdf2 v1.0.0 // indirect
+	github.com/xdg-go/scram v1.1.2 // indirect
+	github.com/xdg-go/stringprep v1.0.4 // indirect
+	github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect
+	github.com/yassinebenaid/godump v0.11.1 // indirect
+	github.com/youmark/pkcs8 v0.0.0-20240726163527-a2c0da244d78 // indirect
 	github.com/ysmood/fetchup v0.2.3 // indirect
 	github.com/ysmood/goob v0.4.0 // indirect
-	github.com/ysmood/got v0.34.1 // indirect
+	github.com/ysmood/got v0.40.0 // indirect
 	github.com/ysmood/gson v0.7.3 // indirect
-	github.com/ysmood/leakless v0.8.0 // indirect
-	github.com/yuin/goldmark v1.5.4 // indirect
-	github.com/yuin/goldmark-emoji v1.0.1 // indirect
+	github.com/ysmood/leakless v0.9.0 // indirect
+	github.com/yuin/goldmark v1.7.13 // indirect
+	github.com/yuin/goldmark-emoji v1.0.6 // indirect
 	github.com/yusufpapurcu/wmi v1.2.4 // indirect
-	github.com/zcalusic/sysinfo v1.0.2 // indirect
-	github.com/zeebo/blake3 v0.2.3 // indirect
+	github.com/zcalusic/sysinfo v1.1.3 // indirect
+	github.com/zeebo/blake3 v0.2.4 // indirect
 	github.com/zmap/rc2 v0.0.0-20190804163417-abaa70531248 // indirect
-	github.com/zmap/zcrypto v0.0.0-20230422215203-9a665e1e9968 // indirect
-	go.etcd.io/bbolt v1.3.7 // indirect
+	github.com/zmap/zcrypto v0.0.0-20240803002437-3a861682ac77 // indirect
+	github.com/zmap/zgrab2 v0.1.8 // indirect
+	gitlab.com/gitlab-org/api/client-go v1.9.1 // indirect
+	go.etcd.io/bbolt v1.4.3 // indirect
+	go.mongodb.org/mongo-driver v1.17.9 // indirect
+	go.opentelemetry.io/auto/sdk v1.2.1 // indirect
+	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.68.0 // indirect
+	go.opentelemetry.io/otel v1.43.0 // indirect
+	go.opentelemetry.io/otel/metric v1.43.0 // indirect
+	go.opentelemetry.io/otel/trace v1.43.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
-	go.uber.org/zap v1.25.0 // indirect
+	go.uber.org/zap v1.27.0 // indirect
+	go.uber.org/zap/exp v0.3.0 // indirect
+	go4.org v0.0.0-20230225012048-214862532bf5 // indirect
 	goftp.io/server/v2 v2.0.1 // indirect
-	golang.org/x/crypto v0.46.0 // indirect
-	golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842 // indirect
-	golang.org/x/mod v0.30.0 // indirect
-	golang.org/x/net v0.48.0 // indirect
+	golang.org/x/arch v0.3.0 // indirect
+	golang.org/x/crypto v0.53.0 // indirect
+	golang.org/x/exp v0.0.0-20260527015227-08cc5374adb3 // indirect
+	golang.org/x/mod v0.36.0 // indirect
 	golang.org/x/oauth2 v0.34.0 // indirect
-	golang.org/x/sync v0.19.0 // indirect
-	golang.org/x/sys v0.39.0 // indirect
-	golang.org/x/term v0.38.0 // indirect
-	golang.org/x/text v0.32.0 // indirect
-	golang.org/x/time v0.5.0 // indirect
-	golang.org/x/tools v0.39.0 // indirect
-	google.golang.org/appengine v1.6.7 // indirect
-	google.golang.org/protobuf v1.33.0 // indirect
+	golang.org/x/sync v0.21.0 // indirect
+	golang.org/x/sys v0.46.0 // indirect
+	golang.org/x/term v0.44.0 // indirect
+	golang.org/x/text v0.38.0 // indirect
+	golang.org/x/tools v0.45.0 // indirect
+	google.golang.org/appengine v1.6.8 // indirect
+	google.golang.org/protobuf v1.36.11 // indirect
 	gopkg.in/alecthomas/kingpin.v2 v2.2.6 // indirect
 	gopkg.in/corvus-ch/zbase32.v1 v1.0.0 // indirect
-	gopkg.in/djherbis/times.v1 v1.3.0 // indirect
+	gopkg.in/warnings.v0 v0.1.2 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
+	mellium.im/sasl v0.3.2 // indirect
 	moul.io/http2curl v1.0.0 // indirect
+	software.sslmate.com/src/go-pkcs12 v0.7.0 // indirect
 )

internal/config/config.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
@@ -13,6 +13,7 @@
 package config
 
 import (
+	"os"
 	"time"
 
 	"github.com/charmbracelet/log"
@@ -21,7 +22,16 @@ import (
 
 type Settings struct {
 	Dirlist           string
+	DirMatchCodes     string // -mc dirlist: status codes to keep
+	DirFilterCodes    string // -fc dirlist: status codes to drop
+	DirFilterSizes    string // -fs dirlist: body sizes to drop
+	DirFilterWords    string // -fw dirlist: word counts to drop
+	DirFilterRegex    string // -fr dirlist: regex; body match drops response
+	Calibrate         bool   // -ac auto-calibrate the soft-404 baseline (dirlist, sql)
+	DirWordlist       string // -w  dirlist: custom wordlist (file path or url)
+	DirExtensions     string // -e  dirlist: extensions appended to each word
 	Dnslist           string
+	Resolvers         string // -resolvers dnslist: comma list overriding the bundled pool
 	Debug             bool
 	LogDir            string
 	NoScan            bool
@@ -39,18 +49,55 @@ type Settings struct {
 	Template          string
 	CMS               bool
 	Headers           bool
+	SecurityHeaders   bool
 	CloudStorage      bool
 	SubdomainTakeover bool
 	Shodan            bool
+	SecurityTrails    bool
 	SQL               bool
 	LFI               bool
+	JWT               bool
+	OpenAPI           bool
+	Favicon           bool
+	CORS              bool
+	Redirect          bool
+	XSS               bool
 	Framework         bool
+	Crawl             bool
+	CrawlDepth        int
+	Passive           bool
+	Probe             bool
+	SARIF             string // path to write a sarif 2.1.0 report to ("" = off)
+	Markdown          string // path to write a markdown report to ("" = off)
+	Silent            bool   // route chrome to stderr, print one finding per line to stdout
+	Diff              bool   // surface only findings added/removed vs the last snapshot
+	Store             string // snapshot dir for diff mode ("" = default state dir)
 	Modules           string // Comma-separated list of module IDs to run
 	ModuleTags        string // Run modules matching these tags
 	AllModules        bool   // Run all loaded modules
 	ListModules       bool   // List available modules and exit
+	Proxy             string
+	Header            goflags.StringSlice // custom request headers ("Key: Value")
+	Cookie            string
+	RateLimit         int
+	Notify            bool   // -notify: ship findings to configured providers
+	NotifySeverity    string // -notify-severity: minimum severity to send (info..critical)
+	NotifyConfig      string // -notify-config: path to a notify-compatible yaml file
 }
 
+// minThreads is the floor for the worker count. Threads feeds wg.Add across the
+// scanners, so 0 silently runs nothing and a negative value panics with
+// "negative WaitGroup counter"; clamp the parsed value up to this.
+const minThreads = 1
+
+// defaultCrawlDepth bounds how far the spider recurses by default; deep enough
+// to find linked pages without crawling an entire site.
+const defaultCrawlDepth = 2
+
+// defaultNotifySeverity is the floor notify sends at when -notify-severity is
+// unset: medium drops pure recon/info noise so alerts stay actionable.
+const defaultNotifySeverity = "medium"
+
 const (
 	Nil goflags.EnumVariable = iota
 
@@ -64,9 +111,9 @@ const (
 	Full
 )
 
-func Parse() *Settings {
-	settings := &Settings{}
-
+// registerFlags builds the flag set for the given settings without parsing it,
+// so callers (Parse and tests) can inspect the registered flags.
+func registerFlags(settings *Settings) *goflags.FlagSet {
 	flagSet := goflags.NewFlagSet()
 	flagSet.SetDescription("a blazing-fast pentesting (recon/exploitation) suite")
 
@@ -79,7 +126,16 @@ func Parse() *Settings {
 	portScopes := goflags.AllowdTypes{"common": Common, "full": Full, "none": Nil}
 	flagSet.CreateGroup("scans", "Scans",
 		flagSet.EnumVar(&settings.Dirlist, "dirlist", Nil, "Directory fuzzing scan size (small/medium/large)", listSizes),
+		flagSet.StringVar(&settings.DirMatchCodes, "mc", "", "Dirlist: match these status codes (comma list, e.g. 200,301)"),
+		flagSet.StringVar(&settings.DirFilterCodes, "fc", "", "Dirlist: filter out these status codes (comma list)"),
+		flagSet.StringVar(&settings.DirFilterSizes, "fs", "", "Dirlist: filter out responses of these body sizes (comma list)"),
+		flagSet.StringVar(&settings.DirFilterWords, "fw", "", "Dirlist: filter out responses with these word counts (comma list)"),
+		flagSet.StringVar(&settings.DirFilterRegex, "fr", "", "Dirlist: filter out responses whose body matches this regex"),
+		flagSet.BoolVar(&settings.Calibrate, "ac", false, "Auto-calibrate the soft-404 wildcard baseline (dirlist, sql)"),
+		flagSet.StringVar(&settings.DirWordlist, "w", "", "Dirlist: custom wordlist (local file path or url; overrides -dirlist size)"),
+		flagSet.StringVar(&settings.DirExtensions, "e", "", "Dirlist: extensions appended to each word (comma list, e.g. php,bak,env)"),
 		flagSet.EnumVar(&settings.Dnslist, "dnslist", Nil, "DNS fuzzing scan size (small/medium/large)", listSizes),
+		flagSet.StringVar(&settings.Resolvers, "resolvers", "", "Dnslist: DNS resolvers to use (comma list, e.g. 1.1.1.1,8.8.8.8; overrides the bundled pool)"),
 		flagSet.EnumVar(&settings.Ports, "ports", Nil, "Port scanning scope (common/full)", portScopes),
 		flagSet.BoolVar(&settings.Dorking, "dork", false, "Enable Google dorking"),
 		flagSet.BoolVar(&settings.Git, "git", false, "Enable git repository scanning"),
@@ -89,12 +145,24 @@ func Parse() *Settings {
 		flagSet.BoolVar(&settings.JavaScript, "js", false, "Enable JavaScript scans"),
 		flagSet.BoolVar(&settings.CMS, "cms", false, "Enable CMS detection"),
 		flagSet.BoolVar(&settings.Headers, "headers", false, "Enable HTTP Header Analysis"),
+		flagSet.BoolVarP(&settings.SecurityHeaders, "security-headers", "sh", false, "Enable security header analysis (missing/weak headers)"),
 		flagSet.BoolVar(&settings.CloudStorage, "c3", false, "Enable C3 Misconfiguration Scan"),
 		flagSet.BoolVar(&settings.SubdomainTakeover, "st", false, "Enable Subdomain Takeover Check"),
 		flagSet.BoolVar(&settings.Shodan, "shodan", false, "Enable Shodan lookup (requires SHODAN_API_KEY env var)"),
+		flagSet.BoolVar(&settings.SecurityTrails, "securitytrails", false, "Enable SecurityTrails domain discovery (requires SECURITYTRAILS_API_KEY env var)"),
 		flagSet.BoolVar(&settings.SQL, "sql", false, "Enable SQL reconnaissance (admin panels, error disclosure)"),
 		flagSet.BoolVar(&settings.LFI, "lfi", false, "Enable LFI (Local File Inclusion) reconnaissance"),
+		flagSet.BoolVar(&settings.JWT, "jwt", false, "Enable JWT discovery + offline weakness analysis"),
+		flagSet.BoolVar(&settings.OpenAPI, "openapi", false, "Enable OpenAPI/Swagger spec exposure probe"),
+		flagSet.BoolVar(&settings.Favicon, "favicon", false, "Enable favicon hash fingerprinting (shodan-style)"),
+		flagSet.BoolVar(&settings.CORS, "cors", false, "Enable CORS misconfiguration probe"),
+		flagSet.BoolVar(&settings.Redirect, "redirect", false, "Enable open redirect probe"),
+		flagSet.BoolVar(&settings.XSS, "xss", false, "Enable reflected XSS probe"),
 		flagSet.BoolVar(&settings.Framework, "framework", false, "Enable framework detection"),
+		flagSet.BoolVar(&settings.Crawl, "crawl", false, "Enable web crawling (spider same-host links/scripts/forms)"),
+		flagSet.IntVar(&settings.CrawlDepth, "crawl-depth", defaultCrawlDepth, "Max crawl recursion depth"),
+		flagSet.BoolVar(&settings.Passive, "passive", false, "Enable passive subdomain/url discovery (zero traffic to target)"),
+		flagSet.BoolVar(&settings.Probe, "probe", false, "Probe the target for liveness (status, title, server, redirect chain)"),
 	)
 
 	flagSet.CreateGroup("runtime", "Runtime",
@@ -102,11 +170,32 @@ func Parse() *Settings {
 		flagSet.DurationVarP(&settings.Timeout, "timeout", "t", 10*time.Second, "HTTP request timeout"),
 		flagSet.StringVarP(&settings.LogDir, "log", "l", "", "Directory to store logs in"),
 		flagSet.IntVar(&settings.Threads, "threads", 10, "Number of threads to run scans on"),
-		flagSet.StringVar(&settings.Template, "template", "", "Sif runtime template to use"),
+		flagSet.StringVar(&settings.Template, "template", "", "Load scan settings from a template (preset minimal/recon/full, or a local yaml file)"),
+	)
+
+	flagSet.CreateGroup("http", "HTTP",
+		flagSet.StringVar(&settings.Proxy, "proxy", "", "Proxy for all requests (http/https/socks5 url)"),
+		flagSet.StringSliceVarP(&settings.Header, "header", "H", nil, "Custom header to send (repeatable or comma-separated, \"Key: Value\")", goflags.CommaSeparatedStringSliceOptions),
+		flagSet.StringVar(&settings.Cookie, "cookie", "", "Cookie header to send with every request"),
+		flagSet.IntVar(&settings.RateLimit, "rate-limit", 0, "Max requests per second (0 = unlimited)"),
+	)
+
+	flagSet.CreateGroup("output", "Output",
+		flagSet.StringVar(&settings.SARIF, "sarif", "", "Write a SARIF 2.1.0 report to this file"),
+		flagSet.StringVarP(&settings.Markdown, "markdown", "md", "", "Write a markdown report to this file"),
+		flagSet.BoolVar(&settings.Silent, "silent", false, "Plain output: chrome to stderr, one finding per line to stdout (for pipelines)"),
+		flagSet.BoolVar(&settings.Diff, "diff", false, "Diff mode: surface only findings added/removed since the last snapshot of each target"),
+		flagSet.StringVar(&settings.Store, "store", "", "Snapshot directory for -diff (default: log dir, else <user-config>/sif/state)"),
+	)
+
+	flagSet.CreateGroup("notify", "Notify",
+		flagSet.BoolVar(&settings.Notify, "notify", false, "Ship findings to configured providers (slack/discord/telegram/webhook)"),
+		flagSet.StringVar(&settings.NotifySeverity, "notify-severity", defaultNotifySeverity, "Minimum severity to notify on (info/low/medium/high/critical)"),
+		flagSet.StringVar(&settings.NotifyConfig, "notify-config", "", "Path to a notify-compatible yaml config (overrides env vars)"),
 	)
 
 	flagSet.CreateGroup("api", "API",
-		flagSet.BoolVar(&settings.ApiMode, "api", false, "Enable API mode. Only useful for internal lunchcat usage"),
+		flagSet.BoolVar(&settings.ApiMode, "api", false, "Enable API mode. Only useful for internal usage"),
 	)
 
 	flagSet.CreateGroup("modules", "Modules",
@@ -116,8 +205,38 @@ func Parse() *Settings {
 		flagSet.BoolVarP(&settings.ListModules, "list-modules", "lm", false, "List available modules and exit"),
 	)
 
-	if err := flagSet.Parse(); err != nil {
-		log.Fatalf("Could not parse flags: %s", err)
+	return flagSet
+}
+
+func Parse() *Settings {
+	settings := &Settings{}
+	flagSet := registerFlags(settings)
+
+	// -template presets a batch of scans from a yaml file or named preset; point
+	// goflags at it before Parse so it merges as config (cli flags still win) and
+	// replaces the ambient config for this run.
+	templatePath, cleanup, err := templateConfigPath(os.Args[1:])
+	if err != nil {
+		log.Fatalf("Could not load template: %s", err)
+	}
+	if templatePath != "" {
+		flagSet.SetConfigFilePath(templatePath)
+	}
+
+	// Parse merges the template config synchronously, so a temp preset file can
+	// be removed right after, before any fatal exit (no leaking defer).
+	parseErr := flagSet.Parse()
+	if cleanup != nil {
+		cleanup()
+	}
+	if parseErr != nil {
+		log.Fatalf("Could not parse flags: %s", parseErr)
+	}
+
+	// threads feeds wg.Add directly; floor it so 0 isn't a silent no-op and a
+	// negative value can't panic the waitgroup.
+	if settings.Threads < minThreads {
+		settings.Threads = minThreads
 	}
 
 	return settings

internal/config/config_test.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
@@ -61,6 +61,14 @@ func TestSettingsDefaults(t *testing.T) {
 	if settings.Ports != "" {
 		t.Errorf("expected Ports default to be empty, got %v", settings.Ports)
 	}
+
+	// diff mode is opt-in and its store dir defaults empty (resolved at runtime).
+	if settings.Diff != false {
+		t.Errorf("expected Diff default to be false, got %v", settings.Diff)
+	}
+	if settings.Store != "" {
+		t.Errorf("expected Store default to be empty, got %v", settings.Store)
+	}
 }
 
 func TestSettingsNoScanBehavior(t *testing.T) {

internal/config/template.go

@@ -0,0 +1,116 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package config
+
+import (
+	"embed"
+	"fmt"
+	"os"
+	"strings"
+)
+
+//go:embed templates/*.yaml
+var embeddedTemplates embed.FS
+
+// presetNames are the templates shipped in the binary, listed in help and
+// error text. each presets a batch of scans without listing every flag.
+var presetNames = []string{"minimal", "recon", "full"}
+
+// templateConfigPath resolves the -template value into a config file path for
+// goflags to merge, plus a cleanup to run after Parse (embedded presets are
+// written to a temp file). it returns "" when -template is unset.
+func templateConfigPath(args []string) (string, func(), error) {
+	value := templateFlagValue(args)
+	if value == "" {
+		return "", nil, nil
+	}
+	return resolveTemplate(value)
+}
+
+// templateFlagValue pulls the -template value out of raw args; the config path
+// has to be known before Parse, so it cannot come from the parsed flag itself.
+func templateFlagValue(args []string) string {
+	for i, arg := range args {
+		if arg == "-template" || arg == "--template" {
+			if i+1 < len(args) {
+				return args[i+1]
+			}
+			return ""
+		}
+		if v, ok := strings.CutPrefix(arg, "-template="); ok {
+			return v
+		}
+		if v, ok := strings.CutPrefix(arg, "--template="); ok {
+			return v
+		}
+	}
+	return ""
+}
+
+// resolveTemplate turns the -template value into a config file path. an existing
+// local file wins; a named preset is materialized from the embedded set; a
+// path-shaped miss or an unknown name is a hard error.
+func resolveTemplate(value string) (string, func(), error) {
+	info, err := os.Stat(value) //nolint:gosec // G304: user-supplied local template path, by design (same as the -f/-w wordlist paths)
+	switch {
+	case err == nil && info.IsDir():
+		return "", nil, fmt.Errorf("template path %q is a directory", value)
+	case err == nil:
+		return value, nil, nil
+	}
+	if data, ok := embeddedPreset(value); ok {
+		return materializePreset(data)
+	}
+	if looksLikePath(value) {
+		return "", nil, fmt.Errorf("template file %q not found", value)
+	}
+	return "", nil, fmt.Errorf("unknown template %q; use a local yaml file or one of: %s",
+		value, strings.Join(presetNames, ", "))
+}
+
+// embeddedPreset returns the bytes of a named preset shipped in the binary.
+func embeddedPreset(name string) ([]byte, bool) {
+	data, err := embeddedTemplates.ReadFile("templates/" + name + ".yaml")
+	if err != nil {
+		return nil, false
+	}
+	return data, true
+}
+
+// materializePreset writes preset bytes to a temp file so goflags, which merges
+// a config by path, can read it; the cleanup removes the file after Parse.
+func materializePreset(data []byte) (string, func(), error) {
+	file, err := os.CreateTemp("", "sif-template-*.yaml")
+	if err != nil {
+		return "", nil, err
+	}
+	cleanup := func() { _ = os.Remove(file.Name()) }
+	if _, err := file.Write(data); err != nil {
+		cleanup()
+		return "", nil, err
+	}
+	if err := file.Close(); err != nil {
+		cleanup()
+		return "", nil, err
+	}
+	return file.Name(), cleanup, nil
+}
+
+// looksLikePath reports whether the value addresses a file rather than a named
+// preset: a path separator or a yaml suffix marks a file.
+func looksLikePath(value string) bool {
+	if strings.ContainsAny(value, `/\`) {
+		return true
+	}
+	return strings.HasSuffix(value, ".yaml") || strings.HasSuffix(value, ".yml")
+}

internal/config/template_test.go

@@ -0,0 +1,211 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package config
+
+import (
+	"flag"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/projectdiscovery/goflags"
+	"gopkg.in/yaml.v3"
+)
+
+// writeTemplate drops a yaml template in a temp dir and returns its path.
+func writeTemplate(t *testing.T, body string) string {
+	t.Helper()
+	path := filepath.Join(t.TempDir(), "tmpl.yaml")
+	if err := os.WriteFile(path, []byte(body), 0o600); err != nil {
+		t.Fatalf("write template: %s", err)
+	}
+	return path
+}
+
+// loadPreset registers the real flags, merges the named embedded preset, and
+// returns the resulting settings (no cli scan flags set).
+func loadPreset(t *testing.T, name string) *Settings {
+	t.Helper()
+	goflags.DisableAutoConfigMigration = true
+	path, cleanup, err := resolveTemplate(name)
+	if err != nil {
+		t.Fatalf("resolve %s: %s", name, err)
+	}
+	if cleanup != nil {
+		defer cleanup()
+	}
+	settings := &Settings{}
+	flagSet := registerFlags(settings)
+	flagSet.SetConfigFilePath(path)
+	if err := flagSet.Parse("-silent"); err != nil {
+		t.Fatalf("parse %s: %s", name, err)
+	}
+	return settings
+}
+
+// every key in an embedded preset must be a real flag long-name. goflags drops
+// unknown config keys silently, so a typo would otherwise ship as a dead no-op.
+func TestPresetKeysAreRegisteredFlags(t *testing.T) {
+	valid := map[string]bool{}
+	registerFlags(&Settings{}).CommandLine.VisitAll(func(f *flag.Flag) {
+		valid[f.Name] = true
+	})
+
+	for _, name := range presetNames {
+		data, ok := embeddedPreset(name)
+		if !ok {
+			t.Errorf("preset %q is not embedded", name)
+			continue
+		}
+		var keys map[string]any
+		if err := yaml.Unmarshal(data, &keys); err != nil {
+			t.Errorf("preset %q is not valid yaml: %s", name, err)
+			continue
+		}
+		for key := range keys {
+			if !valid[key] {
+				t.Errorf("preset %q references unknown flag %q", name, key)
+			}
+		}
+	}
+}
+
+func TestPresetMinimal(t *testing.T) {
+	s := loadPreset(t, "minimal")
+	if !s.Probe || !s.Headers || !s.Favicon {
+		t.Errorf("minimal should enable probe/headers/favicon, got probe=%v headers=%v favicon=%v",
+			s.Probe, s.Headers, s.Favicon)
+	}
+	if s.XSS || s.SQL || s.Nuclei {
+		t.Error("minimal should not enable heavy or intrusive scans")
+	}
+}
+
+func TestPresetReconIsNonIntrusive(t *testing.T) {
+	s := loadPreset(t, "recon")
+	if !s.Passive || !s.Whois || !s.CMS || !s.Probe {
+		t.Errorf("recon should enable passive/whois/cms/probe, got %v/%v/%v/%v",
+			s.Passive, s.Whois, s.CMS, s.Probe)
+	}
+	if s.XSS || s.SQL || s.LFI || s.Redirect {
+		t.Errorf("recon must not enable payload-injecting scans: xss=%v sql=%v lfi=%v redirect=%v",
+			s.XSS, s.SQL, s.LFI, s.Redirect)
+	}
+}
+
+func TestPresetFull(t *testing.T) {
+	s := loadPreset(t, "full")
+	if !s.XSS || !s.SQL || !s.LFI || !s.Redirect {
+		t.Error("full should enable the intrusive scans")
+	}
+	if s.Dirlist != "large" || s.Ports != "full" {
+		t.Errorf("full should set dirlist=large ports=full, got dirlist=%q ports=%q",
+			s.Dirlist, s.Ports)
+	}
+}
+
+// the template merges as the goflags config: it fills flags left at their
+// default, an explicit cli flag still wins, and an untouched flag stays put.
+func TestTemplateConfigPrecedence(t *testing.T) {
+	goflags.DisableAutoConfigMigration = true
+	tmpl := writeTemplate(t, "cms: true\nthreads: 99\n")
+
+	var cms, sql bool
+	var threads int
+	flagSet := goflags.NewFlagSet()
+	flagSet.BoolVar(&cms, "cms", false, "")
+	flagSet.BoolVar(&sql, "sql", false, "")
+	flagSet.IntVar(&threads, "threads", 10, "")
+
+	flagSet.SetConfigFilePath(tmpl)
+	if err := flagSet.Parse("-threads", "5"); err != nil {
+		t.Fatalf("parse: %s", err)
+	}
+
+	if !cms {
+		t.Error("expected template to set cms=true")
+	}
+	if threads != 5 {
+		t.Errorf("expected cli threads 5 to win over template, got %d", threads)
+	}
+	if sql {
+		t.Error("expected sql left untouched to stay false")
+	}
+}
+
+func TestTemplateFlagValue(t *testing.T) {
+	cases := []struct {
+		name string
+		args []string
+		want string
+	}{
+		{"long with space", []string{"-template", "a.yaml"}, "a.yaml"},
+		{"double dash with space", []string{"--template", "b.yaml"}, "b.yaml"},
+		{"long with equals", []string{"-template=c.yaml"}, "c.yaml"},
+		{"double dash with equals", []string{"--template=d.yaml"}, "d.yaml"},
+		{"absent", []string{"-u", "x"}, ""},
+		{"trailing without value", []string{"-u", "x", "-template"}, ""},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := templateFlagValue(tc.args); got != tc.want {
+				t.Errorf("expected %q, got %q", tc.want, got)
+			}
+		})
+	}
+}
+
+func TestResolveTemplateExistingFile(t *testing.T) {
+	path := writeTemplate(t, "cms: true\n")
+	got, cleanup, err := resolveTemplate(path)
+	if cleanup != nil {
+		defer cleanup()
+	}
+	if err != nil {
+		t.Fatalf("resolveTemplate: %s", err)
+	}
+	if got != path {
+		t.Errorf("expected %q, got %q", path, got)
+	}
+}
+
+func TestResolveTemplateNamedPreset(t *testing.T) {
+	path, cleanup, err := resolveTemplate("recon")
+	if cleanup != nil {
+		defer cleanup()
+	}
+	if err != nil {
+		t.Fatalf("recon preset should resolve: %s", err)
+	}
+	if path == "" {
+		t.Fatal("expected a materialized preset path")
+	}
+}
+
+func TestResolveTemplateMissingFile(t *testing.T) {
+	if _, _, err := resolveTemplate("./does-not-exist.yaml"); err == nil {
+		t.Fatal("expected an error for a missing template file")
+	}
+}
+
+func TestResolveTemplateDirectory(t *testing.T) {
+	if _, _, err := resolveTemplate(t.TempDir()); err == nil {
+		t.Fatal("expected an error for a directory")
+	}
+}
+
+func TestResolveTemplateUnknownName(t *testing.T) {
+	if _, _, err := resolveTemplate("bogus"); err == nil {
+		t.Fatal("expected an error for an unknown template name")
+	}
+}

internal/config/templates/full.yaml

@@ -0,0 +1,28 @@
+# full: thorough and active, including intrusive probes that inject payloads
+# (xss, sql, lfi, redirect). api-key scans (shodan, securitytrails) stay opt-in
+# via their own flags.
+passive: true
+whois: true
+dork: true
+favicon: true
+headers: true
+security-headers: true
+cms: true
+framework: true
+probe: true
+git: true
+js: true
+nuclei: true
+openapi: true
+cors: true
+jwt: true
+c3: true
+st: true
+crawl: true
+sql: true
+lfi: true
+xss: true
+redirect: true
+dirlist: large
+dnslist: large
+ports: full

internal/config/templates/minimal.yaml

@@ -0,0 +1,4 @@
+# minimal: fast liveness + fingerprint, a handful of benign GETs per target.
+probe: true
+headers: true
+favicon: true

internal/config/templates/recon.yaml

@@ -0,0 +1,11 @@
+# recon: broad non-intrusive discovery (light traffic, no attack payloads).
+passive: true
+whois: true
+dork: true
+favicon: true
+headers: true
+security-headers: true
+cms: true
+framework: true
+probe: true
+dnslist: small

internal/dnsx/dnsx.go

@@ -0,0 +1,270 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+// Package dnsx resolves subdomain candidates against a bundled resolver pool
+// before anything is probed over http, so the slow/inaccurate path of HTTP-ing
+// every wordlist entry through the OS resolver is gone. it also fingerprints
+// wildcard zones (a zone that answers every random label) so a catch-all
+// nameserver can't flood the caller with phantom subdomains.
+package dnsx
+
+import (
+	"crypto/rand"
+	"fmt"
+	"math/big"
+	"sort"
+	"strings"
+
+	retryabledns "github.com/projectdiscovery/retryabledns"
+)
+
+// bundled default resolver pool. anycast cloudflare/google/quad9 - fast, public,
+// and unlikely to rate-limit a recon sweep. -resolvers overrides this set.
+const (
+	resolverCloudflare = "1.1.1.1:53"
+	resolverGoogle     = "8.8.8.8:53"
+	resolverQuad9      = "9.9.9.9:53"
+)
+
+// defaultResolvers is the bundled pool used when the caller passes none.
+var defaultResolvers = []string{resolverCloudflare, resolverGoogle, resolverQuad9}
+
+const (
+	// defaultRetries is how many times retryabledns rotates through the pool on a
+	// timeout before giving up on a name. low enough to stay fast on a big list.
+	defaultRetries = 3
+
+	// wildcardProbes is how many random nonexistent labels we resolve to
+	// fingerprint a wildcard zone. more samples make a rotating catch-all (one
+	// that hands back a different ip per query) harder to miss, but each is a
+	// real lookup so this stays small.
+	wildcardProbes = 3
+
+	// randomLabelLen is the length of each random wildcard-probe label. long
+	// enough that a collision with a real host is astronomically unlikely.
+	randomLabelLen = 16
+)
+
+// randomLabelAlphabet is the lowercase-alnum set wildcard probe labels draw
+// from; a valid dns label so the query isn't rejected before it leaves.
+const randomLabelAlphabet = "abcdefghijklmnopqrstuvwxyz0123456789"
+
+// defaultDNSPort is appended to any resolver entry given without an explicit
+// port, so "1.1.1.1" and "1.1.1.1:53" both work on the cli.
+const defaultDNSPort = "53"
+
+// ParseResolvers splits a comma list of resolvers into a normalized slice,
+// appending the default port to bare ips/hosts. an empty or blank input returns
+// nil so the caller falls back to the bundled pool.
+func ParseResolvers(raw string) []string {
+	if strings.TrimSpace(raw) == "" {
+		return nil
+	}
+	parts := strings.Split(raw, ",")
+	out := make([]string, 0, len(parts))
+	for i := 0; i < len(parts); i++ {
+		entry := strings.TrimSpace(parts[i])
+		if entry == "" {
+			continue
+		}
+		// a bare ip/host gets the default port; an entry already carrying ":port"
+		// (or a bracketed ipv6 literal) is left as-is.
+		if !strings.Contains(entry, ":") {
+			entry += ":" + defaultDNSPort
+		}
+		out = append(out, entry)
+	}
+
+	return out
+}
+
+// resolution is the resolved address set for one host. empty Addrs means the
+// name did not resolve (nxdomain / no records).
+type resolution struct {
+	Addrs []string
+}
+
+// resolved reports whether the name returned any address.
+func (r resolution) resolved() bool {
+	return len(r.Addrs) > 0
+}
+
+// resolverFn is the test seam: every lookup the package makes goes through this
+// var, so a fake can answer without touching the network. real runs point it at
+// a retryabledns-backed client via NewResolver.
+var resolverFn func(host string) (resolution, error)
+
+// Resolver resolves candidates against a pool and filters wildcard answers. it
+// is built once per scan and shared across the worker goroutines; the
+// underlying retryabledns client is safe for concurrent use.
+type Resolver struct {
+	// wildcardSigs holds the address sets a wildcard zone answers random labels
+	// with. nil/empty means the zone is not wildcard. a candidate whose answer is
+	// covered by one of these is a catch-all hit, not a real host.
+	wildcardSigs []map[string]struct{}
+}
+
+// NewResolver wires resolverFn to a retryabledns client over the given pool
+// (bundled default when resolvers is empty) and returns a Resolver. it does not
+// fingerprint anything yet - call FingerprintWildcard with the apex first.
+func NewResolver(resolvers []string) (*Resolver, error) {
+	pool := resolvers
+	if len(pool) == 0 {
+		pool = defaultResolvers
+	}
+
+	client, err := retryabledns.New(pool, defaultRetries)
+	if err != nil {
+		return nil, fmt.Errorf("dnsx: build resolver over %v: %w", pool, err)
+	}
+
+	// only install the real client when a test hasn't already injected a fake;
+	// the seam wins so hermetic tests never reach this client.
+	if resolverFn == nil {
+		resolverFn = func(host string) (resolution, error) {
+			data, err := client.Resolve(host)
+			if err != nil {
+				return resolution{}, fmt.Errorf("dnsx: resolve %q: %w", host, err)
+			}
+			return resolution{Addrs: mergeAddrs(data)}, nil
+		}
+	}
+
+	return &Resolver{}, nil
+}
+
+// FingerprintWildcard resolves wildcardProbes random labels under apex. any that
+// answer mean the zone is a catch-all, so their address sets are recorded as
+// signatures to filter real candidates against later. a clean zone leaves the
+// signature list empty and nothing gets filtered.
+func (r *Resolver) FingerprintWildcard(apex string) error {
+	apex = strings.TrimSuffix(apex, ".")
+	for i := 0; i < wildcardProbes; i++ {
+		label, err := randomLabel(randomLabelLen)
+		if err != nil {
+			return fmt.Errorf("dnsx: wildcard probe label: %w", err)
+		}
+
+		res, err := resolverFn(label + "." + apex)
+		if err != nil {
+			// a probe failure (timeout / nxdomain surfaced as error) just means this
+			// sample says "not wildcard"; don't abort the whole fingerprint on it.
+			continue
+		}
+		if res.resolved() {
+			r.wildcardSigs = append(r.wildcardSigs, toSet(res.Addrs))
+		}
+	}
+
+	return nil
+}
+
+// Resolve looks up host and reports whether it is a real, non-wildcard hit. a
+// name that doesn't resolve, or whose answer matches a recorded wildcard
+// signature, returns false so the caller skips probing it.
+func (r *Resolver) Resolve(host string) (bool, error) {
+	res, err := resolverFn(host)
+	if err != nil {
+		return false, fmt.Errorf("dnsx: resolve %q: %w", host, err)
+	}
+	if !res.resolved() {
+		return false, nil
+	}
+	if r.isWildcard(res.Addrs) {
+		return false, nil
+	}
+
+	return true, nil
+}
+
+// isWildcard reports whether addrs is covered by any recorded wildcard
+// signature. a candidate whose every address appears in a wildcard answer is a
+// catch-all hit; a host with even one address outside the signature is a real,
+// distinct record and survives.
+func (r *Resolver) isWildcard(addrs []string) bool {
+	if len(r.wildcardSigs) == 0 {
+		return false
+	}
+	for i := 0; i < len(r.wildcardSigs); i++ {
+		if subset(addrs, r.wildcardSigs[i]) {
+			return true
+		}
+	}
+
+	return false
+}
+
+// mergeAddrs flattens the A and AAAA answers into one sorted, deduped slice so
+// two equal answers compare equal regardless of record ordering.
+func mergeAddrs(data *retryabledns.DNSData) []string {
+	if data == nil {
+		return nil
+	}
+	seen := make(map[string]struct{}, len(data.A)+len(data.AAAA))
+	for i := 0; i < len(data.A); i++ {
+		seen[data.A[i]] = struct{}{}
+	}
+	for i := 0; i < len(data.AAAA); i++ {
+		seen[data.AAAA[i]] = struct{}{}
+	}
+
+	addrs := make([]string, 0, len(seen))
+	for addr := range seen {
+		addrs = append(addrs, addr)
+	}
+	sort.Strings(addrs)
+
+	return addrs
+}
+
+// toSet turns addrs into a lookup set for subset checks.
+func toSet(addrs []string) map[string]struct{} {
+	set := make(map[string]struct{}, len(addrs))
+	for i := 0; i < len(addrs); i++ {
+		set[addrs[i]] = struct{}{}
+	}
+
+	return set
+}
+
+// subset reports whether every addr is present in sig (and addrs is non-empty);
+// an empty addrs can't be a wildcard match.
+func subset(addrs []string, sig map[string]struct{}) bool {
+	if len(addrs) == 0 {
+		return false
+	}
+	for i := 0; i < len(addrs); i++ {
+		if _, ok := sig[addrs[i]]; !ok {
+			return false
+		}
+	}
+
+	return true
+}
+
+// randomLabel returns a cryptographically-random lowercase-alnum dns label of
+// length n. crypto/rand (not math/rand) so a target can't predict the probe
+// labels and special-case them to defeat wildcard detection.
+func randomLabel(n int) (string, error) {
+	var b strings.Builder
+	b.Grow(n)
+	alphabetLen := big.NewInt(int64(len(randomLabelAlphabet)))
+	for i := 0; i < n; i++ {
+		idx, err := rand.Int(rand.Reader, alphabetLen)
+		if err != nil {
+			return "", fmt.Errorf("dnsx: random index: %w", err)
+		}
+		b.WriteByte(randomLabelAlphabet[idx.Int64()])
+	}
+
+	return b.String(), nil
+}

internal/dnsx/dnsx_test.go

@@ -0,0 +1,176 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package dnsx
+
+import (
+	"reflect"
+	"strings"
+	"testing"
+)
+
+// withFakeResolver swaps resolverFn for fn for the duration of one test, then
+// restores it - the seam that keeps every case below network-free.
+func withFakeResolver(t *testing.T, fn func(host string) (resolution, error)) {
+	t.Helper()
+	orig := resolverFn
+	resolverFn = fn
+	t.Cleanup(func() { resolverFn = orig })
+}
+
+// newFingerprinted builds a Resolver and runs the wildcard fingerprint against
+// apex using the already-injected fake; fatal on error.
+func newFingerprinted(t *testing.T, apex string) *Resolver {
+	t.Helper()
+	r := &Resolver{}
+	if err := r.FingerprintWildcard(apex); err != nil {
+		t.Fatalf("FingerprintWildcard: %v", err)
+	}
+
+	return r
+}
+
+const testApex = "example.com"
+
+// a host that resolves to a real address, in a clean (non-wildcard) zone, is a
+// genuine hit.
+func TestResolve_FoundInCleanZone(t *testing.T) {
+	withFakeResolver(t, func(host string) (resolution, error) {
+		// nothing answers a random wildcard probe -> clean zone.
+		if strings.HasSuffix(host, "."+testApex) && host != "www."+testApex {
+			return resolution{}, nil
+		}
+		if host == "www."+testApex {
+			return resolution{Addrs: []string{"93.184.216.34"}}, nil
+		}
+		return resolution{}, nil
+	})
+
+	r := newFingerprinted(t, testApex)
+	if len(r.wildcardSigs) != 0 {
+		t.Fatalf("clean zone should record no wildcard signatures, got %d", len(r.wildcardSigs))
+	}
+
+	ok, err := r.Resolve("www." + testApex)
+	if err != nil {
+		t.Fatalf("Resolve: %v", err)
+	}
+	if !ok {
+		t.Error("a resolving host in a clean zone should be a hit")
+	}
+}
+
+// nxdomain (no addresses) is not a hit, so the caller skips probing it.
+func TestResolve_NxdomainSkipped(t *testing.T) {
+	withFakeResolver(t, func(string) (resolution, error) {
+		// every name, probes included, returns no records.
+		return resolution{}, nil
+	})
+
+	r := newFingerprinted(t, testApex)
+
+	ok, err := r.Resolve("ghost." + testApex)
+	if err != nil {
+		t.Fatalf("Resolve: %v", err)
+	}
+	if ok {
+		t.Error("an nxdomain host must not count as found")
+	}
+}
+
+// a wildcard zone answers the random probe labels, so a candidate that resolves
+// to the same catch-all address is filtered out.
+func TestResolve_WildcardFiltered(t *testing.T) {
+	const catchAll = "10.0.0.1"
+	withFakeResolver(t, func(string) (resolution, error) {
+		// the zone answers everything - probes and candidates alike - with one ip.
+		return resolution{Addrs: []string{catchAll}}, nil
+	})
+
+	r := newFingerprinted(t, testApex)
+	if len(r.wildcardSigs) == 0 {
+		t.Fatal("wildcard zone should record at least one signature")
+	}
+
+	ok, err := r.Resolve("anything." + testApex)
+	if err != nil {
+		t.Fatalf("Resolve: %v", err)
+	}
+	if ok {
+		t.Error("a candidate matching the wildcard answer must be filtered")
+	}
+}
+
+// a real host in a wildcard zone that resolves to a distinct address (not the
+// catch-all) still survives the filter - one address outside the signature is
+// enough to be a genuine record.
+func TestResolve_DistinctHostSurvivesWildcard(t *testing.T) {
+	const catchAll = "10.0.0.1"
+	const realHost = "api." + testApex
+	withFakeResolver(t, func(host string) (resolution, error) {
+		if host == realHost {
+			return resolution{Addrs: []string{"203.0.113.7"}}, nil
+		}
+		// everything else (probes + other candidates) hits the catch-all.
+		return resolution{Addrs: []string{catchAll}}, nil
+	})
+
+	r := newFingerprinted(t, testApex)
+	if len(r.wildcardSigs) == 0 {
+		t.Fatal("wildcard zone should record at least one signature")
+	}
+
+	ok, err := r.Resolve(realHost)
+	if err != nil {
+		t.Fatalf("Resolve: %v", err)
+	}
+	if !ok {
+		t.Error("a host resolving to a distinct address should survive the wildcard filter")
+	}
+}
+
+func TestParseResolvers(t *testing.T) {
+	tests := []struct {
+		name string
+		in   string
+		want []string
+	}{
+		{"empty falls back to bundled", "", nil},
+		{"blank falls back to bundled", "   ", nil},
+		{"bare ips get default port", "1.1.1.1,8.8.8.8", []string{"1.1.1.1:53", "8.8.8.8:53"}},
+		{"explicit port preserved", "9.9.9.9:5353", []string{"9.9.9.9:5353"}},
+		{"whitespace and empties trimmed", " 1.1.1.1 , ,8.8.8.8 ", []string{"1.1.1.1:53", "8.8.8.8:53"}},
+		{"mixed bare and ported", "1.1.1.1,9.9.9.9:5353", []string{"1.1.1.1:53", "9.9.9.9:5353"}},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := ParseResolvers(tt.in); !reflect.DeepEqual(got, tt.want) {
+				t.Errorf("ParseResolvers(%q) = %v, want %v", tt.in, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestNewResolver_DefaultsToBundledPool(t *testing.T) {
+	// keep the seam already installed so New doesn't replace it with a real
+	// client; we only assert the constructor accepts an empty override.
+	withFakeResolver(t, func(string) (resolution, error) { return resolution{}, nil })
+
+	r, err := NewResolver(nil)
+	if err != nil {
+		t.Fatalf("NewResolver(nil): %v", err)
+	}
+	if r == nil {
+		t.Fatal("NewResolver returned nil resolver")
+	}
+}

internal/finding/finding.go

@@ -0,0 +1,730 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+// Package finding is the one normalization layer between the scan results and
+// the consumers that don't want to know about ~two dozen result structs: notify
+// (later) gates and renders on it, diff (later) keys runs off it. Flatten is the
+// single type-switch; adding a scanner without teaching Flatten about it trips
+// the guard test in flatten_test.go, on purpose.
+package finding
+
+import (
+	"fmt"
+	"strings"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+	"github.com/dropalldatabases/sif/internal/scan"
+	"github.com/dropalldatabases/sif/internal/scan/frameworks"
+	"github.com/dropalldatabases/sif/internal/scan/js"
+	"github.com/projectdiscovery/nuclei/v3/pkg/output"
+)
+
+// Finding is the normalized shape every scanner result collapses to. one
+// Finding is one underlying item (a single header, one cors hit, one nuclei
+// match) rather than a whole module's blob, so consumers diff and notify at
+// item granularity.
+type Finding struct {
+	Target   string   // the url/host the scan ran against
+	Module   string   // the ResultType() of the source scanner
+	Severity Severity // ranked severity, SeverityUnknown when the source has none
+	Key      string   // stable identity for dedup/diff: module + ":" + identifier
+	Title    string   // short human label
+	Raw      string   // short evidence string, not the full body
+}
+
+// Line renders a finding as one stable, terse, machine-friendly line for the
+// -silent plain sink: "[severity] target module title". no styling, no color -
+// a downstream pipe (notify, grep, awk) keys off the bracketed severity and the
+// fixed field order, so the shape stays frozen. pointer receiver: Finding is
+// wide enough that copying it per line is wasteful.
+func (f *Finding) Line() string {
+	return fmt.Sprintf("[%s] %s %s %s", f.Severity, f.Target, f.Module, f.Title)
+}
+
+// static per-module severities for results that carry no severity field of
+// their own. these are the editorial baseline; a scanner that emits its own
+// severity (cors, xss, nuclei, ...) overrides this on a per-item basis.
+const (
+	// a live admin panel / takeover / public bucket is high on its own.
+	sevTakeover   = SeverityHigh
+	sevPublicS3   = SeverityHigh
+	sevAdminPanel = SeverityHigh
+	// disclosure-grade signals: dberrors, secrets, supabase keys.
+	sevDBError = SeverityMedium
+	sevSecret  = SeverityMedium
+	// pure recon/inventory: headers, crawl urls, passive hosts, ports.
+	sevRecon = SeverityInfo
+)
+
+// keySep joins the module id and the per-item identifier into a Key. kept as a
+// const so the diff layer can split on it without re-deriving the separator.
+const keySep = ":"
+
+// key builds a stable per-item identity: module:identifier. identifier is
+// whatever uniquely names the item within its module (a url, a header name, a
+// subdomain) so the same finding across two runs produces the same Key.
+func key(module, identifier string) string {
+	return module + keySep + identifier
+}
+
+// Flatten normalizes one module's result into zero or more Findings. result is
+// the raw data carried in a ModuleResult; the type switch covers every scan
+// result struct. an unrecognized type yields a single SeverityUnknown finding
+// keyed "module:unhandled" so a new scanner surfaces loudly instead of
+// vanishing - the guard test asserts this never happens for a known type.
+func Flatten(target, module string, result any) []Finding {
+	switch r := result.(type) {
+	case *scan.ShodanResult:
+		return flattenShodan(target, r)
+	case *scan.SQLResult:
+		return flattenSQL(target, r)
+	case *scan.LFIResult:
+		return flattenLFI(target, r)
+	case *scan.JWTResult:
+		return flattenJWT(target, r)
+	case *scan.OpenAPIResult:
+		return flattenOpenAPI(target, r)
+	case *scan.FaviconResult:
+		return flattenFavicon(target, r)
+	case *scan.CMSResult:
+		return flattenCMS(target, r)
+	case *scan.SecurityTrailsResult:
+		return flattenSecurityTrails(target, r)
+	case *scan.CORSResult:
+		return flattenCORS(target, r)
+	case *scan.RedirectResult:
+		return flattenRedirect(target, r)
+	case *scan.XSSResult:
+		return flattenXSS(target, r)
+	case *scan.CrawlResult:
+		return flattenCrawl(target, r)
+	case *scan.PassiveResult:
+		return flattenPassive(target, r)
+	case *scan.ProbeResult:
+		return flattenProbe(target, r)
+	case scan.HeaderResults:
+		return flattenHeaders(target, r)
+	case []scan.HeaderResult:
+		// the headers module appends a literal []HeaderResult, not the named
+		// slice type; both reach here so cover both.
+		return flattenHeaders(target, r)
+	case scan.SecurityHeaderResults:
+		return flattenSecurityHeaders(target, r)
+	case []scan.SecurityHeaderResult:
+		return flattenSecurityHeaders(target, r)
+	case scan.DirectoryResults:
+		return flattenDirlist(target, r)
+	case []scan.DirectoryResult:
+		return flattenDirlist(target, r)
+	case scan.CloudStorageResults:
+		return flattenCloudStorage(target, r)
+	case []scan.CloudStorageResult:
+		return flattenCloudStorage(target, r)
+	case scan.DorkResults:
+		return flattenDork(target, r)
+	case []scan.DorkResult:
+		return flattenDork(target, r)
+	case scan.SubdomainTakeoverResults:
+		return flattenTakeover(target, r)
+	case []scan.SubdomainTakeoverResult:
+		return flattenTakeover(target, r)
+	case *frameworks.FrameworkResult:
+		return flattenFramework(target, r)
+	case *js.JavascriptScanResult:
+		return flattenJS(target, r)
+	case *modules.Result:
+		// yaml/builtin modules carry their own module id; honor it over the
+		// passed-in module so per-module findings stay attributed correctly.
+		return flattenModule(target, r)
+	case []output.ResultEvent:
+		return flattenNuclei(target, r)
+	case []string:
+		// dnslist/portscan/git all hand back a bare []string of discovered
+		// items; module disambiguates which inventory it is.
+		return flattenStrings(target, module, r)
+	default:
+		// unknown type: emit a loud placeholder rather than dropping it.
+		return []Finding{{
+			Target:   target,
+			Module:   module,
+			Severity: SeverityUnknown,
+			Key:      key(module, "unhandled"),
+			Title:    fmt.Sprintf("unhandled result type %T", result),
+			Raw:      fmt.Sprintf("%T", result),
+		}}
+	}
+}
+
+func flattenShodan(target string, r *scan.ShodanResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	// one host snapshot -> one inventory finding; vulns are the interesting bit
+	// so they bump severity and ride along in the evidence string.
+	sev := sevRecon
+	if len(r.Vulns) > 0 {
+		sev = SeverityHigh
+	}
+	raw := fmt.Sprintf("%d ports", len(r.Ports))
+	if len(r.Vulns) > 0 {
+		raw = fmt.Sprintf("%s, %d vulns", raw, len(r.Vulns))
+	}
+	return []Finding{{
+		Target:   target,
+		Module:   "shodan",
+		Severity: sev,
+		Key:      key("shodan", r.IP),
+		Title:    "shodan host " + r.IP,
+		Raw:      raw,
+	}}
+}
+
+func flattenSQL(target string, r *scan.SQLResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.AdminPanels)+len(r.DatabaseErrors)+len(r.ExposedPorts))
+	for i := 0; i < len(r.AdminPanels); i++ {
+		p := r.AdminPanels[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "sql",
+			Severity: sevAdminPanel,
+			Key:      key("sql", "admin:"+p.URL),
+			Title:    p.Type + " admin panel",
+			Raw:      fmt.Sprintf("%s (%d)", p.URL, p.Status),
+		})
+	}
+	for i := 0; i < len(r.DatabaseErrors); i++ {
+		e := r.DatabaseErrors[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "sql",
+			Severity: sevDBError,
+			Key:      key("sql", "dberr:"+e.URL+":"+e.DatabaseType),
+			Title:    e.DatabaseType + " error disclosure",
+			Raw:      e.ErrorPattern,
+		})
+	}
+	for i := 0; i < len(r.ExposedPorts); i++ {
+		p := r.ExposedPorts[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "sql",
+			Severity: SeverityMedium,
+			Key:      key("sql", fmt.Sprintf("port:%d", p)),
+			Title:    fmt.Sprintf("exposed db port %d", p),
+			Raw:      fmt.Sprintf("%d", p),
+		})
+	}
+	return out
+}
+
+func flattenLFI(target string, r *scan.LFIResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.Vulnerabilities))
+	for i := 0; i < len(r.Vulnerabilities); i++ {
+		v := r.Vulnerabilities[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "lfi",
+			Severity: ParseSeverity(v.Severity),
+			Key:      key("lfi", v.URL+":"+v.Parameter),
+			Title:    "lfi via " + v.Parameter,
+			Raw:      v.Evidence,
+		})
+	}
+	return out
+}
+
+func flattenJWT(target string, r *scan.JWTResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.Tokens))
+	for i := 0; i < len(r.Tokens); i++ {
+		t := r.Tokens[i]
+		// one finding per weakness, not per token: a token with alg:none and a
+		// weak key is two distinct issues a consumer wants to diff separately.
+		for j := 0; j < len(t.Issues); j++ {
+			iss := t.Issues[j]
+			out = append(out, Finding{
+				Target:   target,
+				Module:   "jwt",
+				Severity: ParseSeverity(iss.Severity),
+				Key:      key("jwt", t.Source+":"+iss.Kind),
+				Title:    "jwt " + iss.Kind,
+				Raw:      iss.Detail,
+			})
+		}
+	}
+	return out
+}
+
+func flattenOpenAPI(target string, r *scan.OpenAPIResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	return []Finding{{
+		Target:   target,
+		Module:   "openapi",
+		Severity: ParseSeverity(r.Severity),
+		Key:      key("openapi", r.SpecURL),
+		Title:    "openapi spec exposed",
+		Raw:      fmt.Sprintf("%s (%d endpoints)", r.SpecURL, len(r.Endpoints)),
+	}}
+}
+
+func flattenFavicon(target string, r *scan.FaviconResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	// a matched fingerprint is a real signal; an unmatched hash is just inventory
+	// (still useful as a shodan pivot, so we keep it at recon).
+	sev := sevRecon
+	title := fmt.Sprintf("favicon hash %d", r.Hash)
+	if r.Tech != "" {
+		sev = SeverityLow
+		title = r.Tech + " (favicon)"
+	}
+	return []Finding{{
+		Target:   target,
+		Module:   "favicon",
+		Severity: sev,
+		Key:      key("favicon", fmt.Sprintf("%d", r.Hash)),
+		Title:    title,
+		Raw:      r.ShodanQ,
+	}}
+}
+
+func flattenCMS(target string, r *scan.CMSResult) []Finding {
+	if r == nil || r.Name == "" {
+		return nil
+	}
+	return []Finding{{
+		Target:   target,
+		Module:   "cms",
+		Severity: sevRecon,
+		Key:      key("cms", r.Name),
+		Title:    r.Name + " detected",
+		Raw:      strings.TrimSpace(r.Name + " " + r.Version),
+	}}
+}
+
+func flattenSecurityTrails(target string, r *scan.SecurityTrailsResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.Subdomains)+len(r.AssociatedDomains))
+	for i := 0; i < len(r.Subdomains); i++ {
+		d := r.Subdomains[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "securitytrails",
+			Severity: sevRecon,
+			Key:      key("securitytrails", "sub:"+d),
+			Title:    "subdomain " + d,
+			Raw:      d,
+		})
+	}
+	for i := 0; i < len(r.AssociatedDomains); i++ {
+		d := r.AssociatedDomains[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "securitytrails",
+			Severity: sevRecon,
+			Key:      key("securitytrails", "assoc:"+d),
+			Title:    "associated domain " + d,
+			Raw:      d,
+		})
+	}
+	return out
+}
+
+func flattenCORS(target string, r *scan.CORSResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.Findings))
+	for i := 0; i < len(r.Findings); i++ {
+		f := r.Findings[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "cors",
+			Severity: ParseSeverity(f.Severity),
+			Key:      key("cors", f.URL+":"+f.OriginTested),
+			Title:    f.Note,
+			Raw:      "allow-origin: " + f.AllowOrigin,
+		})
+	}
+	return out
+}
+
+func flattenRedirect(target string, r *scan.RedirectResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.Findings))
+	for i := 0; i < len(r.Findings); i++ {
+		f := r.Findings[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "redirect",
+			Severity: ParseSeverity(f.Severity),
+			Key:      key("redirect", f.URL+":"+f.Parameter+":"+f.Via),
+			Title:    "open redirect via " + f.Parameter,
+			Raw:      f.Location,
+		})
+	}
+	return out
+}
+
+func flattenXSS(target string, r *scan.XSSResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.Findings))
+	for i := 0; i < len(r.Findings); i++ {
+		f := r.Findings[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "xss",
+			Severity: ParseSeverity(f.Severity),
+			Key:      key("xss", f.URL+":"+f.Parameter+":"+f.Context),
+			Title:    "reflected xss in " + f.Parameter,
+			Raw:      strings.Join(f.SurvivedRaw, " "),
+		})
+	}
+	return out
+}
+
+func flattenCrawl(target string, r *scan.CrawlResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.URLs))
+	for i := 0; i < len(r.URLs); i++ {
+		u := r.URLs[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "crawl",
+			Severity: sevRecon,
+			Key:      key("crawl", u),
+			Title:    "crawled url",
+			Raw:      u,
+		})
+	}
+	return out
+}
+
+func flattenPassive(target string, r *scan.PassiveResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	out := make([]Finding, 0, len(r.Subdomains)+len(r.URLs))
+	for i := 0; i < len(r.Subdomains); i++ {
+		s := r.Subdomains[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "passive",
+			Severity: sevRecon,
+			Key:      key("passive", "sub:"+s),
+			Title:    "passive subdomain " + s,
+			Raw:      s,
+		})
+	}
+	for i := 0; i < len(r.URLs); i++ {
+		u := r.URLs[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "passive",
+			Severity: sevRecon,
+			Key:      key("passive", "url:"+u),
+			Title:    "passive url",
+			Raw:      u,
+		})
+	}
+	return out
+}
+
+func flattenProbe(target string, r *scan.ProbeResult) []Finding {
+	if r == nil || !r.Alive {
+		// a dead probe isn't a finding, just an absent host.
+		return nil
+	}
+	return []Finding{{
+		Target:   target,
+		Module:   "probe",
+		Severity: sevRecon,
+		Key:      key("probe", r.URL),
+		Title:    fmt.Sprintf("alive %d", r.StatusCode),
+		Raw:      strings.TrimSpace(fmt.Sprintf("%d %s", r.StatusCode, r.Title)),
+	}}
+}
+
+func flattenHeaders(target string, rs []scan.HeaderResult) []Finding {
+	out := make([]Finding, 0, len(rs))
+	for i := 0; i < len(rs); i++ {
+		h := rs[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "headers",
+			Severity: sevRecon,
+			Key:      key("headers", h.Name),
+			Title:    h.Name,
+			Raw:      h.Value,
+		})
+	}
+	return out
+}
+
+func flattenSecurityHeaders(target string, rs []scan.SecurityHeaderResult) []Finding {
+	out := make([]Finding, 0, len(rs))
+	for i := 0; i < len(rs); i++ {
+		h := rs[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "security_headers",
+			Severity: ParseSeverity(h.Severity),
+			Key:      key("security_headers", h.Header),
+			Title:    h.Header,
+			Raw:      h.Note,
+		})
+	}
+	return out
+}
+
+// dirInteresting bounds the "noteworthy" 3xx range for a listed directory; a
+// redirect (>=300) or anything past it is worth more than a plain 200 hit.
+const dirRedirectFloor = 300
+
+func flattenDirlist(target string, rs []scan.DirectoryResult) []Finding {
+	out := make([]Finding, 0, len(rs))
+	for i := 0; i < len(rs); i++ {
+		d := rs[i]
+		sev := sevRecon
+		if d.StatusCode >= dirRedirectFloor {
+			sev = SeverityLow
+		}
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "dirlist",
+			Severity: sev,
+			Key:      key("dirlist", d.Url),
+			Title:    fmt.Sprintf("%s [%d]", d.Url, d.StatusCode),
+			Raw:      fmt.Sprintf("status=%d size=%d", d.StatusCode, d.Size),
+		})
+	}
+	return out
+}
+
+func flattenCloudStorage(target string, rs []scan.CloudStorageResult) []Finding {
+	out := make([]Finding, 0, len(rs))
+	for i := 0; i < len(rs); i++ {
+		b := rs[i]
+		sev := sevRecon
+		if b.IsPublic {
+			sev = sevPublicS3
+		}
+		title := "bucket " + b.BucketName
+		if b.IsPublic {
+			title = "public bucket " + b.BucketName
+		}
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "cloudstorage",
+			Severity: sev,
+			Key:      key("cloudstorage", b.BucketName),
+			Title:    title,
+			Raw:      fmt.Sprintf("public=%t", b.IsPublic),
+		})
+	}
+	return out
+}
+
+func flattenDork(target string, rs []scan.DorkResult) []Finding {
+	out := make([]Finding, 0, len(rs))
+	for i := 0; i < len(rs); i++ {
+		d := rs[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "dork",
+			Severity: sevRecon,
+			Key:      key("dork", d.Url),
+			Title:    "dork hit",
+			Raw:      d.Url,
+		})
+	}
+	return out
+}
+
+func flattenTakeover(target string, rs []scan.SubdomainTakeoverResult) []Finding {
+	out := make([]Finding, 0, len(rs))
+	for i := 0; i < len(rs); i++ {
+		t := rs[i]
+		// only the vulnerable ones are findings; a safe cname is noise here.
+		if !t.Vulnerable {
+			continue
+		}
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "subdomain_takeover",
+			Severity: sevTakeover,
+			Key:      key("subdomain_takeover", t.Subdomain),
+			Title:    "takeover: " + t.Subdomain,
+			Raw:      t.Service,
+		})
+	}
+	return out
+}
+
+func flattenFramework(target string, r *frameworks.FrameworkResult) []Finding {
+	if r == nil || r.Name == "" {
+		return nil
+	}
+	// framework risk maps onto severity; an unset risk falls back to recon.
+	sev := ParseSeverity(r.RiskLevel)
+	if sev == SeverityUnknown {
+		sev = sevRecon
+	}
+	raw := strings.TrimSpace(r.Name + " " + r.Version)
+	if len(r.CVEs) > 0 {
+		raw = fmt.Sprintf("%s, %d cves", raw, len(r.CVEs))
+	}
+	return []Finding{{
+		Target:   target,
+		Module:   "framework",
+		Severity: sev,
+		Key:      key("framework", r.Name),
+		Title:    r.Name + " detected",
+		Raw:      raw,
+	}}
+}
+
+func flattenJS(target string, r *js.JavascriptScanResult) []Finding {
+	if r == nil {
+		return nil
+	}
+	supabase := r.SupabaseFindings()
+	out := make([]Finding, 0, len(r.SecretMatches)+len(supabase)+len(r.Endpoints)+len(r.FoundEnvironmentVars))
+	for i := 0; i < len(r.SecretMatches); i++ {
+		s := r.SecretMatches[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "js",
+			Severity: sevSecret,
+			Key:      key("js", "secret:"+s.Rule+":"+s.Source),
+			Title:    "secret: " + s.Rule,
+			Raw:      s.Source,
+		})
+	}
+	for i := 0; i < len(supabase); i++ {
+		s := supabase[i]
+		// a non-anon role on an exposed key is the real bug; anon is just recon.
+		sev := sevRecon
+		if s.Role != "" && s.Role != "anon" {
+			sev = SeverityHigh
+		}
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "js",
+			Severity: sev,
+			Key:      key("js", "supabase:"+s.ProjectId),
+			Title:    "supabase project " + s.ProjectId,
+			Raw:      fmt.Sprintf("role=%s collections=%d", s.Role, s.Collections),
+		})
+	}
+	for i := 0; i < len(r.Endpoints); i++ {
+		e := r.Endpoints[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "js",
+			Severity: sevRecon,
+			Key:      key("js", "endpoint:"+e),
+			Title:    "js endpoint",
+			Raw:      e,
+		})
+	}
+	// env vars are a map; sort-free since the Key carries the name, and diff
+	// keys on the Key not on iteration order.
+	for name, value := range r.FoundEnvironmentVars {
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "js",
+			Severity: sevSecret,
+			Key:      key("js", "env:"+name),
+			Title:    "env var " + name,
+			Raw:      value,
+		})
+	}
+	return out
+}
+
+func flattenModule(target string, r *modules.Result) []Finding {
+	if r == nil {
+		return nil
+	}
+	module := r.ResultType()
+	out := make([]Finding, 0, len(r.Findings))
+	for i := 0; i < len(r.Findings); i++ {
+		f := r.Findings[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   module,
+			Severity: ParseSeverity(f.Severity),
+			Key:      key(module, f.URL),
+			Title:    module + " finding",
+			Raw:      f.Evidence,
+		})
+	}
+	return out
+}
+
+func flattenNuclei(target string, events []output.ResultEvent) []Finding {
+	out := make([]Finding, 0, len(events))
+	for i := 0; i < len(events); i++ {
+		e := events[i]
+		// host is the most reliable per-hit identifier; matched-at sharpens it
+		// when several templates fire on one host.
+		ident := e.TemplateID + ":" + e.Host
+		if e.Matched != "" {
+			ident = e.TemplateID + ":" + e.Matched
+		}
+		out = append(out, Finding{
+			Target:   target,
+			Module:   "nuclei",
+			Severity: ParseSeverity(e.Info.SeverityHolder.Severity.String()),
+			Key:      key("nuclei", ident),
+			Title:    e.Info.Name,
+			Raw:      e.Matched,
+		})
+	}
+	return out
+}
+
+func flattenStrings(target, module string, items []string) []Finding {
+	out := make([]Finding, 0, len(items))
+	for i := 0; i < len(items); i++ {
+		v := items[i]
+		out = append(out, Finding{
+			Target:   target,
+			Module:   module,
+			Severity: sevRecon,
+			Key:      key(module, v),
+			Title:    module + " item",
+			Raw:      v,
+		})
+	}
+	return out
+}

internal/finding/finding_test.go

@@ -0,0 +1,383 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package finding
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+	"github.com/dropalldatabases/sif/internal/scan"
+	"github.com/dropalldatabases/sif/internal/scan/frameworks"
+	"github.com/dropalldatabases/sif/internal/scan/js"
+	"github.com/projectdiscovery/nuclei/v3/pkg/model"
+	"github.com/projectdiscovery/nuclei/v3/pkg/model/types/severity"
+	"github.com/projectdiscovery/nuclei/v3/pkg/output"
+)
+
+// scanResultType mirrors the minimal interface the scan packages implement; the
+// coverage table below carries a value per ResultType() so a new scanner whose
+// ResultType isn't represented (or isn't handled by Flatten) trips a failure.
+type scanResultType interface {
+	ResultType() string
+}
+
+// coverageCase is one representative, non-empty instance of a result type plus
+// its expected module attribution. wantItems is how many findings Flatten must
+// emit for the populated instance, proving the per-item fan-out works.
+type coverageCase struct {
+	value     any            // the result as it reaches Flatten
+	typed     scanResultType // same value when it implements ResultType(), else nil
+	module    string         // module id Flatten should stamp
+	wantItems int            // findings the populated instance must produce
+}
+
+// coverageCases is the registry the guard checks against. there must be one
+// entry per distinct ResultType() in the scan tree (plus the raw []string and
+// nuclei []ResultEvent that flow through the report without a ResultType). add a
+// scanner without adding it here and TestFlattenCoversEveryResultType fails.
+func coverageCases() []coverageCase {
+	return []coverageCase{
+		{
+			value:     &scan.ShodanResult{IP: "1.2.3.4", Ports: []int{80}, Vulns: []string{"CVE-1"}},
+			typed:     &scan.ShodanResult{},
+			module:    "shodan",
+			wantItems: 1,
+		},
+		{
+			value: &scan.SQLResult{
+				AdminPanels:    []scan.SQLAdminPanel{{URL: "http://x/pma", Type: "phpMyAdmin", Status: 200}},
+				DatabaseErrors: []scan.SQLDatabaseError{{URL: "http://x", DatabaseType: "mysql", ErrorPattern: "syntax"}},
+				ExposedPorts:   []int{3306},
+			},
+			typed:     &scan.SQLResult{},
+			module:    "sql",
+			wantItems: 3,
+		},
+		{
+			value: &scan.LFIResult{Vulnerabilities: []scan.LFIVulnerability{
+				{URL: "http://x", Parameter: "file", Evidence: "root:x", Severity: "high"},
+			}},
+			typed:     &scan.LFIResult{},
+			module:    "lfi",
+			wantItems: 1,
+		},
+		{
+			value: &scan.JWTResult{Tokens: []scan.JWTToken{{
+				Source: "header:Authorization",
+				Alg:    "none",
+				Issues: []scan.JWTIssue{
+					{Kind: "alg:none", Severity: "critical", Detail: "no signature"},
+					{Kind: "missing exp", Severity: "medium", Detail: "no expiry"},
+				},
+			}}},
+			typed:     &scan.JWTResult{},
+			module:    "jwt",
+			wantItems: 2,
+		},
+		{
+			value: &scan.OpenAPIResult{
+				SpecURL:   "http://x/openapi.json",
+				Severity:  "high",
+				Endpoints: []scan.OpenAPIEndpoint{{Path: "/users", Method: "GET", Unauth: true}},
+			},
+			typed:     &scan.OpenAPIResult{},
+			module:    "openapi",
+			wantItems: 1,
+		},
+		{
+			value:     &scan.FaviconResult{Hash: 116323821, Tech: "Apache Tomcat", ShodanQ: "http.favicon.hash:116323821"},
+			typed:     &scan.FaviconResult{},
+			module:    "favicon",
+			wantItems: 1,
+		},
+		{
+			value:     &scan.CMSResult{Name: "WordPress", Version: "6.1"},
+			typed:     &scan.CMSResult{},
+			module:    "cms",
+			wantItems: 1,
+		},
+		{
+			value:     &scan.SecurityTrailsResult{Domain: "x.com", Subdomains: []string{"a.x.com"}, AssociatedDomains: []string{"y.com"}},
+			typed:     &scan.SecurityTrailsResult{},
+			module:    "securitytrails",
+			wantItems: 2,
+		},
+		{
+			value:     &scan.CORSResult{Findings: []scan.CORSFinding{{URL: "http://x", OriginTested: "null", AllowOrigin: "null", Severity: "medium", Note: "null origin"}}},
+			typed:     &scan.CORSResult{},
+			module:    "cors",
+			wantItems: 1,
+		},
+		{
+			value:     &scan.RedirectResult{Findings: []scan.RedirectFinding{{URL: "http://x", Parameter: "next", Location: "http://evil", Via: "header", Severity: "medium"}}},
+			typed:     &scan.RedirectResult{},
+			module:    "redirect",
+			wantItems: 1,
+		},
+		{
+			value:     &scan.XSSResult{Findings: []scan.XSSFinding{{URL: "http://x", Parameter: "q", Context: "html", SurvivedRaw: []string{"<"}, Severity: "high"}}},
+			typed:     &scan.XSSResult{},
+			module:    "xss",
+			wantItems: 1,
+		},
+		{
+			value:     &scan.CrawlResult{URLs: []string{"http://x/a"}},
+			typed:     &scan.CrawlResult{},
+			module:    "crawl",
+			wantItems: 1,
+		},
+		{
+			value:     &scan.PassiveResult{Subdomains: []string{"a.x.com"}, URLs: []string{"http://x/old"}},
+			typed:     &scan.PassiveResult{},
+			module:    "passive",
+			wantItems: 2,
+		},
+		{
+			value:     &scan.ProbeResult{URL: "http://x", Alive: true, StatusCode: 200, Title: "home"},
+			typed:     &scan.ProbeResult{},
+			module:    "probe",
+			wantItems: 1,
+		},
+		{
+			value:     scan.HeaderResults{{Name: "Server", Value: "nginx"}},
+			typed:     scan.HeaderResults{},
+			module:    "headers",
+			wantItems: 1,
+		},
+		{
+			value:     scan.SecurityHeaderResults{{Header: "Content-Security-Policy", Present: false, Severity: "medium", Note: "missing"}},
+			typed:     scan.SecurityHeaderResults{},
+			module:    "security_headers",
+			wantItems: 1,
+		},
+		{
+			value:     scan.DirectoryResults{{Url: "http://x/admin", StatusCode: 301, Size: 10, Words: 2}},
+			typed:     scan.DirectoryResults{},
+			module:    "dirlist",
+			wantItems: 1,
+		},
+		{
+			value:     scan.CloudStorageResults{{BucketName: "x-assets", IsPublic: true}},
+			typed:     scan.CloudStorageResults{},
+			module:    "cloudstorage",
+			wantItems: 1,
+		},
+		{
+			value:     scan.DorkResults{{Url: "http://x/leak", Count: 1}},
+			typed:     scan.DorkResults{},
+			module:    "dork",
+			wantItems: 1,
+		},
+		{
+			value:     scan.SubdomainTakeoverResults{{Subdomain: "old.x.com", Vulnerable: true, Service: "GitHub Pages"}},
+			typed:     scan.SubdomainTakeoverResults{},
+			module:    "subdomain_takeover",
+			wantItems: 1,
+		},
+		{
+			value:     &frameworks.FrameworkResult{Name: "Laravel", Version: "9.0", RiskLevel: "high", CVEs: []string{"CVE-2"}},
+			typed:     &frameworks.FrameworkResult{},
+			module:    "framework",
+			wantItems: 1,
+		},
+		{
+			value: &js.JavascriptScanResult{
+				SecretMatches: []js.SecretMatch{{Rule: "aws-key", Match: "AKIA...", Source: "http://x/app.js"}},
+				Endpoints:     []string{"/api/v1"},
+			},
+			typed:     &js.JavascriptScanResult{},
+			module:    "js",
+			wantItems: 2,
+		},
+		{
+			value:     &modules.Result{ModuleID: "custom-mod", Target: "http://x", Findings: []modules.Finding{{URL: "http://x", Severity: "low", Evidence: "hit"}}},
+			typed:     &modules.Result{ModuleID: "custom-mod"},
+			module:    "custom-mod",
+			wantItems: 1,
+		},
+		{
+			// nuclei results aren't ScanResult-typed; they ride through the report
+			// as a raw []ResultEvent, so cover that shape explicitly.
+			value:     []output.ResultEvent{{TemplateID: "t1", Host: "x", Matched: "http://x", Info: model.Info{Name: "n", SeverityHolder: severity.Holder{Severity: severity.High}}}},
+			module:    "nuclei",
+			wantItems: 1,
+		},
+		{
+			// dnslist/portscan/git all hand Flatten a bare []string keyed only by
+			// the module argument.
+			value:     []string{"sub.x.com"},
+			module:    "dnslist",
+			wantItems: 1,
+		},
+	}
+}
+
+const target = "http://target.example"
+
+// TestFlattenCoversEveryResultType is the guard: every result type in the
+// coverage table must flatten into the expected module without hitting the
+// "unhandled" fallback. a new scanner that skips both the table and Flatten's
+// switch trips this loudly.
+func TestFlattenCoversEveryResultType(t *testing.T) {
+	for _, tc := range coverageCases() {
+		findings := Flatten(target, tc.module, tc.value)
+
+		if len(findings) != tc.wantItems {
+			t.Errorf("module %q: got %d findings, want %d", tc.module, len(findings), tc.wantItems)
+		}
+		for i := 0; i < len(findings); i++ {
+			f := findings[i]
+			if strings.HasSuffix(f.Key, keySep+"unhandled") {
+				t.Errorf("module %q: Flatten has no case, fell through to unhandled (key=%q)", tc.module, f.Key)
+			}
+			if f.Target != target {
+				t.Errorf("module %q: target=%q, want %q", tc.module, f.Target, target)
+			}
+			if f.Module != tc.module {
+				t.Errorf("module %q: finding stamped module=%q, want %q", tc.module, f.Module, tc.module)
+			}
+			if f.Key == "" {
+				t.Errorf("module %q: empty Key", tc.module)
+			}
+			if !strings.HasPrefix(f.Key, tc.module+keySep) {
+				t.Errorf("module %q: Key %q not prefixed with module", tc.module, f.Key)
+			}
+		}
+	}
+}
+
+// TestEveryResultTypeIsInCoverageTable cross-checks the table against the actual
+// ResultType() registry: if a scanner type exists whose ResultType() isn't in
+// the table, the coverage guard above would never exercise it. enumerate the
+// known typed entries and assert each ResultType() string is present.
+func TestEveryResultTypeIsInCoverageTable(t *testing.T) {
+	covered := make(map[string]struct{})
+	for _, tc := range coverageCases() {
+		if tc.typed == nil {
+			continue
+		}
+		covered[tc.typed.ResultType()] = struct{}{}
+	}
+
+	// the full set of ResultType() strings the scan tree exposes. keep this in
+	// lockstep with the ScanResult implementers; a missing entry means the table
+	// (and very likely Flatten) skipped a scanner.
+	want := []string{
+		"shodan", "sql", "lfi", "jwt", "openapi", "favicon", "cms", "securitytrails",
+		"cors", "redirect", "xss", "crawl", "passive", "probe",
+		"headers", "security_headers", "dirlist", "cloudstorage",
+		"dork", "subdomain_takeover", "framework", "js", "custom-mod",
+	}
+	for _, rt := range want {
+		if _, ok := covered[rt]; !ok {
+			t.Errorf("ResultType %q has no entry in coverageCases; Flatten coverage unverified", rt)
+		}
+	}
+}
+
+// TestFlattenStableKeysAndSeverities pins the keys and severities for a couple
+// of representative items so a refactor that quietly reshuffles them is caught.
+func TestFlattenStableKeysAndSeverities(t *testing.T) {
+	tests := []struct {
+		name    string
+		value   any
+		module  string
+		wantKey string
+		wantSev Severity
+	}{
+		{
+			name:    "cors honors source severity",
+			value:   &scan.CORSResult{Findings: []scan.CORSFinding{{URL: "http://x", OriginTested: "null", AllowOrigin: "null", Severity: "high", Note: "n"}}},
+			module:  "cors",
+			wantKey: "cors:http://x:null",
+			wantSev: SeverityHigh,
+		},
+		{
+			name:    "public bucket is high",
+			value:   scan.CloudStorageResults{{BucketName: "b", IsPublic: true}},
+			module:  "cloudstorage",
+			wantKey: "cloudstorage:b",
+			wantSev: SeverityHigh,
+		},
+		{
+			name:    "header is recon info",
+			value:   scan.HeaderResults{{Name: "Server", Value: "nginx"}},
+			module:  "headers",
+			wantKey: "headers:Server",
+			wantSev: SeverityInfo,
+		},
+		{
+			name:    "vulnerable takeover is high",
+			value:   scan.SubdomainTakeoverResults{{Subdomain: "old.x.com", Vulnerable: true, Service: "GitHub Pages"}},
+			module:  "subdomain_takeover",
+			wantKey: "subdomain_takeover:old.x.com",
+			wantSev: SeverityHigh,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			findings := Flatten(target, tt.module, tt.value)
+			if len(findings) != 1 {
+				t.Fatalf("got %d findings, want 1", len(findings))
+			}
+			f := findings[0]
+			if f.Key != tt.wantKey {
+				t.Errorf("Key = %q, want %q", f.Key, tt.wantKey)
+			}
+			if f.Severity != tt.wantSev {
+				t.Errorf("Severity = %v, want %v", f.Severity, tt.wantSev)
+			}
+		})
+	}
+}
+
+// TestFlattenUnhandledTypeIsLoud asserts the fallback fires for a type Flatten
+// doesn't know - this is what makes the guard above meaningful.
+func TestFlattenUnhandledTypeIsLoud(t *testing.T) {
+	type bogus struct{}
+	findings := Flatten(target, "mystery", bogus{})
+	if len(findings) != 1 {
+		t.Fatalf("got %d findings, want 1 placeholder", len(findings))
+	}
+	if !strings.HasSuffix(findings[0].Key, keySep+"unhandled") {
+		t.Errorf("unhandled type should key on :unhandled, got %q", findings[0].Key)
+	}
+	if findings[0].Severity != SeverityUnknown {
+		t.Errorf("unhandled severity = %v, want SeverityUnknown", findings[0].Severity)
+	}
+}
+
+// TestSubdomainTakeoverSkipsSafe confirms a non-vulnerable cname produces no
+// finding; only the real takeover is a finding.
+func TestSubdomainTakeoverSkipsSafe(t *testing.T) {
+	value := scan.SubdomainTakeoverResults{
+		{Subdomain: "safe.x.com", Vulnerable: false},
+		{Subdomain: "bad.x.com", Vulnerable: true, Service: "Heroku"},
+	}
+	findings := Flatten(target, "subdomain_takeover", value)
+	if len(findings) != 1 {
+		t.Fatalf("got %d findings, want 1 (only the vulnerable one)", len(findings))
+	}
+	if findings[0].Key != "subdomain_takeover:bad.x.com" {
+		t.Errorf("Key = %q, want subdomain_takeover:bad.x.com", findings[0].Key)
+	}
+}
+
+// TestDeadProbeIsNotAFinding confirms a host that didn't answer yields nothing.
+func TestDeadProbeIsNotAFinding(t *testing.T) {
+	findings := Flatten(target, "probe", &scan.ProbeResult{URL: "http://x", Alive: false})
+	if len(findings) != 0 {
+		t.Errorf("dead probe produced %d findings, want 0", len(findings))
+	}
+}

internal/finding/line_test.go

@@ -0,0 +1,48 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package finding
+
+import "testing"
+
+// Line is the -silent wire format; its shape is frozen, so pin it.
+func TestFindingLine(t *testing.T) {
+	tests := []struct {
+		name string
+		f    Finding
+		want string
+	}{
+		{
+			name: "high severity",
+			f:    Finding{Target: "https://x.com", Module: "sql", Severity: SeverityHigh, Title: "admin panel"},
+			want: "[high] https://x.com sql admin panel",
+		},
+		{
+			name: "info recon",
+			f:    Finding{Target: "https://y.com", Module: "headers", Severity: SeverityInfo, Title: "Server"},
+			want: "[info] https://y.com headers Server",
+		},
+		{
+			name: "unknown severity",
+			f:    Finding{Target: "z.com", Module: "mystery", Severity: SeverityUnknown, Title: "?"},
+			want: "[unknown] z.com mystery ?",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := tt.f.Line(); got != tt.want {
+				t.Errorf("Line() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}

internal/finding/severity.go

@@ -0,0 +1,78 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package finding
+
+import "strings"
+
+// Severity is an ordered severity rank shared by every normalized finding.
+// the order matters: notify gates on a threshold and diff sorts by it, so the
+// underlying ints have to compare info < low < medium < high < critical.
+type Severity int
+
+// severity ranks, lowest to highest. SeverityUnknown sorts below everything so
+// an unrecognized scanner string never silently outranks a real critical.
+const (
+	SeverityUnknown Severity = iota
+	SeverityInfo
+	SeverityLow
+	SeverityMedium
+	SeverityHigh
+	SeverityCritical
+)
+
+// severityNames maps each rank to its canonical lowercase string. the wire
+// format scanners emit ("info"/"low"/...) round-trips through this table.
+var severityNames = map[Severity]string{
+	SeverityUnknown:  "unknown",
+	SeverityInfo:     "info",
+	SeverityLow:      "low",
+	SeverityMedium:   "medium",
+	SeverityHigh:     "high",
+	SeverityCritical: "critical",
+}
+
+// String renders the canonical lowercase name for the rank.
+func (s Severity) String() string {
+	if name, ok := severityNames[s]; ok {
+		return name
+	}
+	return severityNames[SeverityUnknown]
+}
+
+// ParseSeverity maps a scanner's free-form severity string onto a rank. it's
+// case/space insensitive and folds the common synonyms ("informational",
+// "warning", "moderate") so the dozen scanners that each picked their own
+// spelling all land on the same ladder. an empty or unrecognized value is
+// SeverityUnknown rather than a guess.
+func ParseSeverity(raw string) Severity {
+	switch strings.ToLower(strings.TrimSpace(raw)) {
+	case "critical":
+		return SeverityCritical
+	case "high":
+		return SeverityHigh
+	case "medium", "moderate", "warning":
+		return SeverityMedium
+	case "low":
+		return SeverityLow
+	case "info", "informational", "information", "none":
+		return SeverityInfo
+	default:
+		return SeverityUnknown
+	}
+}
+
+// AtLeast reports whether s is at or above threshold; notify uses it to drop
+// findings below the configured floor.
+func (s Severity) AtLeast(threshold Severity) bool {
+	return s >= threshold
+}

internal/finding/severity_test.go

@@ -0,0 +1,84 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package finding
+
+import "testing"
+
+func TestParseSeverity(t *testing.T) {
+	tests := []struct {
+		in   string
+		want Severity
+	}{
+		{"critical", SeverityCritical},
+		{"CRITICAL", SeverityCritical},
+		{"  high  ", SeverityHigh},
+		{"medium", SeverityMedium},
+		{"moderate", SeverityMedium},
+		{"warning", SeverityMedium},
+		{"low", SeverityLow},
+		{"info", SeverityInfo},
+		{"informational", SeverityInfo},
+		{"none", SeverityInfo},
+		{"", SeverityUnknown},
+		{"bogus", SeverityUnknown},
+	}
+	for _, tt := range tests {
+		if got := ParseSeverity(tt.in); got != tt.want {
+			t.Errorf("ParseSeverity(%q) = %v, want %v", tt.in, got, tt.want)
+		}
+	}
+}
+
+func TestSeverityOrdering(t *testing.T) {
+	// the ladder must be strictly increasing for AtLeast/sort to behave.
+	ordered := []Severity{
+		SeverityUnknown, SeverityInfo, SeverityLow,
+		SeverityMedium, SeverityHigh, SeverityCritical,
+	}
+	for i := 1; i < len(ordered); i++ {
+		if ordered[i-1] >= ordered[i] {
+			t.Errorf("severity ladder not increasing at %d: %v !< %v", i, ordered[i-1], ordered[i])
+		}
+	}
+}
+
+func TestSeverityAtLeast(t *testing.T) {
+	tests := []struct {
+		sev       Severity
+		threshold Severity
+		want      bool
+	}{
+		{SeverityHigh, SeverityMedium, true},
+		{SeverityMedium, SeverityMedium, true},
+		{SeverityLow, SeverityMedium, false},
+		{SeverityCritical, SeverityInfo, true},
+		{SeverityUnknown, SeverityInfo, false},
+	}
+	for _, tt := range tests {
+		if got := tt.sev.AtLeast(tt.threshold); got != tt.want {
+			t.Errorf("%v.AtLeast(%v) = %v, want %v", tt.sev, tt.threshold, got, tt.want)
+		}
+	}
+}
+
+func TestSeverityStringRoundTrip(t *testing.T) {
+	// every named rank renders to a string ParseSeverity maps back to the same
+	// rank, so the wire format is lossless for known severities.
+	for _, sev := range []Severity{
+		SeverityInfo, SeverityLow, SeverityMedium, SeverityHigh, SeverityCritical,
+	} {
+		if got := ParseSeverity(sev.String()); got != sev {
+			t.Errorf("round-trip %v -> %q -> %v", sev, sev.String(), got)
+		}
+	}
+}

internal/fingerprint/favicon.go

@@ -0,0 +1,56 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+// Package fingerprint holds small response-fingerprinting primitives shared by
+// the scan checks and the module engine, so both compute identical values.
+package fingerprint
+
+import (
+	"encoding/base64"
+	"strings"
+
+	"github.com/twmb/murmur3"
+)
+
+// b64LineLen is python's base64.encodebytes line width. mmh3/shodan hash the
+// chunked base64 (newline every 76 chars, trailing newline), so we must wrap at
+// exactly this width to land on the same hash.
+const b64LineLen = 76
+
+// FaviconHash computes shodan's favicon hash: murmur3 32-bit over the python
+// base64.encodebytes encoding of the raw icon (newline every 76 chars plus a
+// trailing newline), reinterpreted as a signed int32 (both load-bearing, golden-pinned).
+func FaviconHash(data []byte) int32 {
+	encoded := encodeFaviconBase64(data)
+	return int32(murmur3.Sum32(encoded)) //nolint:gosec // shodan stores the signed reinterpretation on purpose
+}
+
+// encodeFaviconBase64 mirrors python's base64.encodebytes: standard base64 with
+// a newline inserted every 76 output characters and a trailing newline. this is
+// the exact byte stream shodan feeds to mmh3, so it must match byte-for-byte.
+func encodeFaviconBase64(data []byte) []byte {
+	raw := base64.StdEncoding.EncodeToString(data)
+
+	var b strings.Builder
+	// final size: the base64 body plus one '\n' per (full or partial) 76-char
+	// line. preallocate so the builder never regrows mid-loop.
+	b.Grow(len(raw) + len(raw)/b64LineLen + 1)
+	for i := 0; i < len(raw); i += b64LineLen {
+		end := i + b64LineLen
+		if end > len(raw) {
+			end = len(raw)
+		}
+		b.WriteString(raw[i:end])
+		b.WriteByte('\n')
+	}
+	return []byte(b.String())
+}

internal/fingerprint/favicon_test.go

@@ -0,0 +1,68 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package fingerprint
+
+import (
+	"strings"
+	"testing"
+)
+
+// goldenFaviconBytes is a fixed payload long enough to span multiple base64
+// lines, so the python-style 76-char chunking is actually exercised by the hash.
+var goldenFaviconBytes = []byte(strings.Repeat("sif-favicon-golden-test-bytes-", 8))
+
+// goldenFaviconHash is the pinned shodan mmh3 hash of goldenFaviconBytes: the python
+// base64.encodebytes byte stream (76-char lines + trailing newline) through murmur3-32,
+// reinterpreted as a signed int32. if the chunking or signedness regress, this test fails.
+const goldenFaviconHash int32 = -1554620260
+
+// goldenHelloHash pins a short single-line case so a regression in the trailing
+// newline (which the small case still has) is caught independently.
+const goldenHelloHash int32 = 1155597304
+
+func TestFaviconHashGolden(t *testing.T) {
+	tests := []struct {
+		name string
+		in   []byte
+		want int32
+	}{
+		{name: "multi-line fixture", in: goldenFaviconBytes, want: goldenFaviconHash},
+		{name: "single-line hello", in: []byte("hello"), want: goldenHelloHash},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := FaviconHash(tt.in); got != tt.want {
+				t.Errorf("FaviconHash = %d, want %d", got, tt.want)
+			}
+		})
+	}
+}
+
+// TestFaviconBase64Chunking pins the encode step against python's
+// base64.encodebytes: a 60-byte input encodes to 80 base64 chars, so it must
+// wrap into two newline-terminated lines.
+func TestFaviconBase64Chunking(t *testing.T) {
+	in := []byte(strings.Repeat("A", 60))
+	got := string(encodeFaviconBase64(in))
+
+	lines := strings.Split(strings.TrimRight(got, "\n"), "\n")
+	if len(lines) != 2 {
+		t.Fatalf("expected 2 wrapped lines, got %d: %q", len(lines), got)
+	}
+	if len(lines[0]) != b64LineLen {
+		t.Errorf("first line = %d chars, want %d", len(lines[0]), b64LineLen)
+	}
+	if !strings.HasSuffix(got, "\n") {
+		t.Errorf("encoding must end in a trailing newline, got %q", got)
+	}
+}

internal/httpx/httpx.go

@@ -0,0 +1,258 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+// Package httpx is the shared http layer every scanner talks through, so a
+// single Configure call wires proxy, custom headers, cookies and rate limiting
+// into every outbound request without touching scanner signatures.
+package httpx
+
+import (
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"net/url"
+	"strings"
+	"sync"
+	"time"
+
+	"golang.org/x/net/proxy"
+	"golang.org/x/time/rate"
+)
+
+// allowed proxy schemes
+const (
+	schemeHTTP   = "http"
+	schemeHTTPS  = "https"
+	schemeSOCKS5 = "socks5"
+)
+
+// a header is "Key: Value"; this is the separator between the two halves.
+const headerSep = ": "
+
+// burst lets the limiter absorb a small spike before pacing kicks in; a burst
+// equal to the per-second rate keeps the cap honest over any one-second window.
+const limiterBurstPerRate = 1
+
+// transport pool tuning. go's default transport caps idle conns per host at 2
+// and reuse only kicks in once a response body is fully drained, so without
+// these a high thread count just thrashes the dialer instead of pooling.
+const (
+	// total idle conns kept warm across every host we hit in a run.
+	maxIdleConns = 512
+	// floor for per-host idle conns so a single-target run still pools even
+	// when the thread count is tiny.
+	minIdleConnsPerHost = 8
+	// how long an idle conn lingers before the pool reaps it.
+	idleConnTimeout = 90 * time.Second
+	// keepalive probe interval for live conns; mirrors go's default dialer so
+	// the socks5 branch doesn't silently lose os-level keepalive.
+	dialKeepAlive = 30 * time.Second
+	// dial timeout for the socks5 branch; matches go's default dialer.
+	dialTimeout = 30 * time.Second
+)
+
+// drainCap bounds how much of an unread body DrainClose will copy before
+// closing; a body larger than this isn't worth slurping just to reuse the
+// conn, so we cap the read and let the conn be discarded instead.
+const drainCap = 16 << 10
+
+// Options carries the runtime knobs that apply to every outbound request.
+// RateLimit is requests/sec (0 = unlimited); Headers are "Key: Value" strings.
+type Options struct {
+	Proxy     string
+	Headers   []string
+	Cookie    string
+	UserAgent string
+	RateLimit int
+	// Threads is the scan worker count; it sizes the per-host idle pool so
+	// concurrent workers hitting one target reuse conns instead of dialing fresh.
+	Threads int
+}
+
+// configured holds the package-level transport built once by Configure. nil
+// means Configure was never called, so Client falls back to a plain client.
+var (
+	mu         sync.RWMutex
+	configured http.RoundTripper
+)
+
+// Configure builds the shared transport once at startup from opts. Calling it
+// again replaces the previous configuration.
+//
+//nolint:gocritic // signature is the package's stable startup api; called once.
+func Configure(opts Options) error {
+	base, err := buildTransport(opts.Proxy, opts.Threads)
+	if err != nil {
+		return err
+	}
+
+	headers, err := parseHeaders(opts.Headers)
+	if err != nil {
+		return err
+	}
+
+	var limiter *rate.Limiter
+	if opts.RateLimit > 0 {
+		limiter = rate.NewLimiter(rate.Limit(opts.RateLimit), opts.RateLimit*limiterBurstPerRate)
+	}
+
+	rt := &roundTripper{
+		base:      base,
+		headers:   headers,
+		cookie:    opts.Cookie,
+		userAgent: opts.UserAgent,
+		limiter:   limiter,
+	}
+
+	mu.Lock()
+	configured = rt
+	mu.Unlock()
+
+	return nil
+}
+
+// Client returns an http client wired to the configured transport. It works
+// before Configure is ever called (plain transport) so existing code and tests
+// behave unchanged. A zero timeout means no timeout, matching http.Client.
+func Client(timeout time.Duration) *http.Client {
+	mu.RLock()
+	rt := configured
+	mu.RUnlock()
+
+	return &http.Client{Timeout: timeout, Transport: rt}
+}
+
+// buildTransport clones the default transport, tunes its pool for the worker
+// count and applies the proxy. An empty proxy leaves the default behavior
+// (respects HTTP_PROXY env) intact.
+func buildTransport(proxyURL string, threads int) (*http.Transport, error) {
+	tr, ok := http.DefaultTransport.(*http.Transport)
+	if !ok {
+		// unreachable in practice, but never trust an assertion silently.
+		return nil, fmt.Errorf("default transport is not *http.Transport")
+	}
+	transport := tr.Clone()
+
+	// size the idle pool so every worker can keep its conn warm. per-host idle
+	// must clear the thread count or workers past the cap re-dial each request;
+	// MaxConnsPerHost stays 0 (unbounded) so the limiter, not the pool, paces us.
+	transport.MaxIdleConns = maxIdleConns
+	transport.MaxIdleConnsPerHost = idlePerHost(threads)
+	transport.MaxConnsPerHost = 0
+	transport.IdleConnTimeout = idleConnTimeout
+	transport.ForceAttemptHTTP2 = true
+
+	if proxyURL == "" {
+		return transport, nil
+	}
+
+	parsed, err := url.Parse(proxyURL)
+	if err != nil {
+		return nil, fmt.Errorf("parse proxy url %q: %w", proxyURL, err)
+	}
+
+	switch parsed.Scheme {
+	case schemeHTTP, schemeHTTPS:
+		transport.Proxy = http.ProxyURL(parsed)
+	case schemeSOCKS5:
+		// socks5 needs a custom dialer. proxy.SOCKS5 takes a forward dialer, so
+		// hand it our own net.Dialer with keepalive set - the default
+		// proxy.Direct has none, which would kill os-level conn pooling.
+		fwd := &net.Dialer{Timeout: dialTimeout, KeepAlive: dialKeepAlive}
+		dialer, err := proxy.SOCKS5("tcp", parsed.Host, nil, fwd)
+		if err != nil {
+			return nil, fmt.Errorf("socks5 proxy %q: %w", proxyURL, err)
+		}
+		ctxDialer, ok := dialer.(proxy.ContextDialer)
+		if !ok {
+			return nil, fmt.Errorf("socks5 proxy %q: dialer lacks context support", proxyURL)
+		}
+		transport.DialContext = ctxDialer.DialContext
+	default:
+		return nil, fmt.Errorf("unsupported proxy scheme %q (want http/https/socks5)", parsed.Scheme)
+	}
+
+	return transport, nil
+}
+
+// idlePerHost picks the per-host idle pool size: at least the worker count so
+// no worker re-dials, never below the floor so a small thread count still pools.
+func idlePerHost(threads int) int {
+	if threads < minIdleConnsPerHost {
+		return minIdleConnsPerHost
+	}
+	return threads
+}
+
+// DrainClose fully reads (up to drainCap) and closes resp.Body. go only returns
+// a conn to the idle pool when the body is read to EOF, so a caller that only
+// closes leaks the conn and forces a fresh dial next time. Call this instead of
+// a bare resp.Body.Close() to keep the pool warm. Safe on a nil response.
+func DrainClose(resp *http.Response) {
+	if resp == nil || resp.Body == nil {
+		return
+	}
+	// the read result is intentionally ignored: we're discarding the body and
+	// about to close it, so a copy error changes nothing we can act on.
+	_, _ = io.Copy(io.Discard, io.LimitReader(resp.Body, drainCap))
+	resp.Body.Close()
+}
+
+// parseHeaders splits each "Key: Value" entry on the first ": ". Entries
+// without the separator are rejected so a typo fails loud instead of silently.
+// The returned map is always non-nil so callers can range it unconditionally.
+func parseHeaders(raw []string) (map[string]string, error) {
+	headers := make(map[string]string, len(raw))
+	for i := 0; i < len(raw); i++ {
+		key, value, ok := strings.Cut(raw[i], headerSep)
+		if !ok {
+			return nil, fmt.Errorf("invalid header %q (want \"Key: Value\")", raw[i])
+		}
+		headers[key] = value
+	}
+
+	return headers, nil
+}
+
+// roundTripper paces and decorates each request before delegating to base.
+type roundTripper struct {
+	base      *http.Transport
+	headers   map[string]string
+	cookie    string
+	userAgent string
+	limiter   *rate.Limiter
+}
+
+func (rt *roundTripper) RoundTrip(req *http.Request) (*http.Response, error) {
+	if rt.limiter != nil {
+		if err := rt.limiter.Wait(req.Context()); err != nil {
+			return nil, fmt.Errorf("rate limiter: %w", err)
+		}
+	}
+
+	// only set what the caller hasn't already; a scanner that explicitly sets a
+	// header (e.g. an api key) must win over the global default.
+	for key, value := range rt.headers {
+		if req.Header.Get(key) == "" {
+			req.Header.Set(key, value)
+		}
+	}
+	if rt.cookie != "" && req.Header.Get("Cookie") == "" {
+		req.Header.Set("Cookie", rt.cookie)
+	}
+	if rt.userAgent != "" && req.Header.Get("User-Agent") == "" {
+		req.Header.Set("User-Agent", rt.userAgent)
+	}
+
+	return rt.base.RoundTrip(req)
+}

internal/httpx/httpx_test.go

@@ -0,0 +1,491 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package httpx
+
+import (
+	"context"
+	"io"
+	"net"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+)
+
+// resetConfig clears the package-level transport so each test starts clean.
+func resetConfig(t *testing.T) {
+	t.Helper()
+	mu.Lock()
+	configured = nil
+	mu.Unlock()
+}
+
+// captureServer records the headers of the last request it served.
+func captureServer(t *testing.T, seen *http.Header) *httptest.Server {
+	t.Helper()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		*seen = r.Header.Clone()
+		w.WriteHeader(http.StatusOK)
+	}))
+	t.Cleanup(srv.Close)
+	return srv
+}
+
+func get(t *testing.T, client *http.Client, url string) {
+	t.Helper()
+	req, err := http.NewRequestWithContext(context.Background(), http.MethodGet, url, http.NoBody)
+	if err != nil {
+		t.Fatalf("new request: %v", err)
+	}
+	resp, err := client.Do(req)
+	if err != nil {
+		t.Fatalf("do request: %v", err)
+	}
+	resp.Body.Close()
+}
+
+func TestClientBeforeConfigure(t *testing.T) {
+	resetConfig(t)
+
+	var seen http.Header
+	srv := captureServer(t, &seen)
+
+	// a client must work with no Configure call so existing code is unaffected.
+	get(t, Client(5*time.Second), srv.URL)
+
+	if seen == nil {
+		t.Fatal("request never reached the server")
+	}
+}
+
+func TestConfigureHeadersAndCookie(t *testing.T) {
+	tests := []struct {
+		name      string
+		opts      Options
+		wantKey   string
+		wantValue string
+	}{
+		{
+			name:      "custom header injected",
+			opts:      Options{Headers: []string{"X-Test: sif"}},
+			wantKey:   "X-Test",
+			wantValue: "sif",
+		},
+		{
+			name:      "cookie injected",
+			opts:      Options{Cookie: "session=abc"},
+			wantKey:   "Cookie",
+			wantValue: "session=abc",
+		},
+		{
+			name:      "user agent injected",
+			opts:      Options{UserAgent: "sif-scanner"},
+			wantKey:   "User-Agent",
+			wantValue: "sif-scanner",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			resetConfig(t)
+
+			if err := Configure(tt.opts); err != nil {
+				t.Fatalf("Configure: %v", err)
+			}
+
+			var seen http.Header
+			srv := captureServer(t, &seen)
+			get(t, Client(5*time.Second), srv.URL)
+
+			if got := seen.Get(tt.wantKey); got != tt.wantValue {
+				t.Errorf("header %q = %q, want %q", tt.wantKey, got, tt.wantValue)
+			}
+		})
+	}
+}
+
+func TestConfigureHeaderDoesNotOverride(t *testing.T) {
+	resetConfig(t)
+
+	if err := Configure(Options{Headers: []string{"X-Test: global"}}); err != nil {
+		t.Fatalf("Configure: %v", err)
+	}
+
+	var seen http.Header
+	srv := captureServer(t, &seen)
+
+	// a caller that sets the header explicitly must win over the global default.
+	req, err := http.NewRequestWithContext(context.Background(), http.MethodGet, srv.URL, http.NoBody)
+	if err != nil {
+		t.Fatalf("new request: %v", err)
+	}
+	req.Header.Set("X-Test", "caller")
+	resp, err := Client(5 * time.Second).Do(req)
+	if err != nil {
+		t.Fatalf("do request: %v", err)
+	}
+	resp.Body.Close()
+
+	if got := seen.Get("X-Test"); got != "caller" {
+		t.Errorf("X-Test = %q, want caller (caller value must not be overridden)", got)
+	}
+}
+
+func TestConfigureInvalidHeader(t *testing.T) {
+	resetConfig(t)
+
+	// a header without ": " should fail loud rather than silently dropping.
+	if err := Configure(Options{Headers: []string{"missing-separator"}}); err == nil {
+		t.Fatal("expected error for malformed header, got nil")
+	}
+}
+
+func TestConfigureInvalidProxy(t *testing.T) {
+	tests := []struct {
+		name  string
+		proxy string
+	}{
+		{name: "unsupported scheme", proxy: "ftp://localhost:1080"},
+		{name: "malformed url", proxy: "://nope"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			resetConfig(t)
+			if err := Configure(Options{Proxy: tt.proxy}); err == nil {
+				t.Errorf("expected error for proxy %q, got nil", tt.proxy)
+			}
+		})
+	}
+}
+
+func TestRateLimit(t *testing.T) {
+	resetConfig(t)
+
+	const ratePerSec = 5
+	if err := Configure(Options{RateLimit: ratePerSec}); err != nil {
+		t.Fatalf("Configure: %v", err)
+	}
+
+	var seen http.Header
+	srv := captureServer(t, &seen)
+	client := Client(5 * time.Second)
+
+	// at 5 req/s the limiter starts with a full burst, so the first batch is
+	// immediate and the next request must wait roughly one tick. fire burst+1
+	// requests and assert the extra one forced a measurable delay.
+	const requests = ratePerSec + 1
+	start := time.Now()
+	for i := 0; i < requests; i++ {
+		get(t, client, srv.URL)
+	}
+	elapsed := time.Since(start)
+
+	// one request beyond the burst should cost about 1/rate; allow slack but
+	// require a non-trivial delay so an unthrottled client fails this.
+	minDelay := time.Second / ratePerSec / 2
+	if elapsed < minDelay {
+		t.Errorf("expected rate limiting to add >= %v of delay, got %v", minDelay, elapsed)
+	}
+}
+
+func TestRateLimitUnlimited(t *testing.T) {
+	resetConfig(t)
+
+	// RateLimit 0 means no limiter is installed; requests should fly through.
+	if err := Configure(Options{RateLimit: 0}); err != nil {
+		t.Fatalf("Configure: %v", err)
+	}
+
+	mu.RLock()
+	rt, ok := configured.(*roundTripper)
+	mu.RUnlock()
+	if !ok {
+		t.Fatal("configured transport is not *roundTripper")
+	}
+	if rt.limiter != nil {
+		t.Error("expected no limiter when RateLimit is 0")
+	}
+}
+
+func TestIdlePerHost(t *testing.T) {
+	tests := []struct {
+		name    string
+		threads int
+		want    int
+	}{
+		{name: "below floor clamps up", threads: 1, want: minIdleConnsPerHost},
+		{name: "zero clamps up", threads: 0, want: minIdleConnsPerHost},
+		{name: "at floor", threads: minIdleConnsPerHost, want: minIdleConnsPerHost},
+		{name: "above floor passes through", threads: 64, want: 64},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := idlePerHost(tt.threads); got != tt.want {
+				t.Errorf("idlePerHost(%d) = %d, want %d", tt.threads, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestBuildTransportTuning(t *testing.T) {
+	const threads = 32
+	tr, err := buildTransport("", threads)
+	if err != nil {
+		t.Fatalf("buildTransport: %v", err)
+	}
+
+	if tr.MaxIdleConns != maxIdleConns {
+		t.Errorf("MaxIdleConns = %d, want %d", tr.MaxIdleConns, maxIdleConns)
+	}
+	if tr.MaxIdleConnsPerHost != threads {
+		t.Errorf("MaxIdleConnsPerHost = %d, want %d", tr.MaxIdleConnsPerHost, threads)
+	}
+	if tr.MaxConnsPerHost != 0 {
+		t.Errorf("MaxConnsPerHost = %d, want 0 (unbounded)", tr.MaxConnsPerHost)
+	}
+	if tr.IdleConnTimeout != idleConnTimeout {
+		t.Errorf("IdleConnTimeout = %v, want %v", tr.IdleConnTimeout, idleConnTimeout)
+	}
+	if !tr.ForceAttemptHTTP2 {
+		t.Error("ForceAttemptHTTP2 = false, want true")
+	}
+}
+
+func TestDrainClose(t *testing.T) {
+	resetConfig(t)
+
+	// serve a body the caller never reads; DrainClose must drain it so the conn
+	// is eligible for reuse rather than abandoned mid-stream.
+	const body = "sif response body that the caller never reads"
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.WriteHeader(http.StatusOK)
+		io.WriteString(w, body)
+	}))
+	t.Cleanup(srv.Close)
+
+	req, err := http.NewRequestWithContext(context.Background(), http.MethodGet, srv.URL, http.NoBody)
+	if err != nil {
+		t.Fatalf("new request: %v", err)
+	}
+	resp, err := Client(5 * time.Second).Do(req)
+	if err != nil {
+		t.Fatalf("do request: %v", err)
+	}
+
+	DrainClose(resp)
+
+	// after DrainClose the body is closed; a further read must fail.
+	if _, err := resp.Body.Read(make([]byte, 1)); err == nil {
+		t.Error("expected read after DrainClose to fail on a closed body")
+	}
+}
+
+func TestDrainCloseNil(t *testing.T) {
+	// a nil response (e.g. an errored request) must not panic.
+	DrainClose(nil)
+	DrainClose(&http.Response{})
+}
+
+// countConns wraps a test server with a ConnState hook that tallies how many
+// distinct tcp conns the server saw. distinct conns == failed reuse.
+func countConns(t *testing.T) (*httptest.Server, func() int) {
+	t.Helper()
+
+	var (
+		mu    sync.Mutex
+		conns = make(map[net.Conn]struct{})
+	)
+	srv := httptest.NewUnstartedServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		// always write a body so reuse depends on the caller draining it.
+		io.WriteString(w, "ok")
+	}))
+	srv.Config.ConnState = func(c net.Conn, state http.ConnState) {
+		if state != http.StateNew {
+			return
+		}
+		mu.Lock()
+		conns[c] = struct{}{}
+		mu.Unlock()
+	}
+	srv.Start()
+	t.Cleanup(srv.Close)
+
+	return srv, func() int {
+		mu.Lock()
+		defer mu.Unlock()
+		return len(conns)
+	}
+}
+
+func TestTransportReusesConnections(t *testing.T) {
+	resetConfig(t)
+
+	const (
+		threads  = 8
+		requests = 30
+	)
+	if err := Configure(Options{Threads: threads}); err != nil {
+		t.Fatalf("Configure: %v", err)
+	}
+
+	srv, distinct := countConns(t)
+
+	// fire N sequential requests through the tuned client, draining each body so
+	// the conn returns to the pool. a working pool serves all of them on one conn.
+	client := Client(5 * time.Second)
+	for i := 0; i < requests; i++ {
+		req, err := http.NewRequestWithContext(context.Background(), http.MethodGet, srv.URL, http.NoBody)
+		if err != nil {
+			t.Fatalf("new request %d: %v", i, err)
+		}
+		resp, err := client.Do(req)
+		if err != nil {
+			t.Fatalf("do request %d: %v", i, err)
+		}
+		DrainClose(resp)
+	}
+
+	// sequential reuse should land on exactly one conn; allow a tiny margin for
+	// the rare race where a conn is reaped between requests.
+	const maxReuseConns = 2
+	if got := distinct(); got > maxReuseConns {
+		t.Errorf("tuned client opened %d conns for %d requests, want <= %d (pool not reusing)",
+			got, requests, maxReuseConns)
+	}
+}
+
+func TestBareClientDoesNotReuse(t *testing.T) {
+	srv, distinct := countConns(t)
+
+	// the control: a bare DefaultTransport client whose caller closes but never
+	// drains the body. go can't reuse a half-read conn, so each request dials
+	// fresh - this is exactly the pre-tuning behavior we're fixing.
+	client := &http.Client{
+		Timeout:   5 * time.Second,
+		Transport: http.DefaultTransport.(*http.Transport).Clone(),
+	}
+
+	const requests = 30
+	for i := 0; i < requests; i++ {
+		req, err := http.NewRequestWithContext(context.Background(), http.MethodGet, srv.URL, http.NoBody)
+		if err != nil {
+			t.Fatalf("new request %d: %v", i, err)
+		}
+		resp, err := client.Do(req)
+		if err != nil {
+			t.Fatalf("do request %d: %v", i, err)
+		}
+		// close without draining - the leak that kills reuse.
+		resp.Body.Close()
+	}
+
+	// most requests should have dialed a fresh conn. don't demand exactly N (the
+	// scheduler occasionally reuses one), just that it's clearly not pooling.
+	const minDistinct = requests / 2
+	if got := distinct(); got < minDistinct {
+		t.Errorf("bare client opened only %d conns for %d requests, want >= %d "+
+			"(expected near-zero reuse without draining)", got, requests, minDistinct)
+	}
+}
+
+// BenchmarkConnReuse contrasts the tuned, draining client against a bare client
+// that closes without draining. the reported conns/op metric is the distinct
+// tcp conns one pass of `requests` opened - tuned≈1, bare≈requests - so the
+// README can quote real before/after reuse numbers. the conn map is reset per
+// iteration so the metric stays a per-pass count and the bare path doesn't
+// accumulate b.N*requests live sockets and exhaust the ephemeral port range.
+//
+// run the bare sub-bench with a bounded -benchtime (e.g. -benchtime 5x): its
+// whole point is that it can't reuse, so a large b.N floods the local port
+// space with TIME_WAIT sockets. the tuned sub-bench reuses and runs unbounded.
+func BenchmarkConnReuse(b *testing.B) {
+	const requests = 50
+
+	run := func(b *testing.B, drain bool, client *http.Client) {
+		b.Helper()
+		var (
+			mu    sync.Mutex
+			conns = make(map[net.Conn]struct{})
+		)
+		srv := httptest.NewUnstartedServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+			io.WriteString(w, strings.Repeat("x", 256))
+		}))
+		srv.Config.ConnState = func(c net.Conn, state http.ConnState) {
+			if state != http.StateNew {
+				return
+			}
+			mu.Lock()
+			conns[c] = struct{}{}
+			mu.Unlock()
+		}
+		srv.Start()
+		defer srv.Close()
+
+		var lastPass int
+		b.ResetTimer()
+		for n := 0; n < b.N; n++ {
+			mu.Lock()
+			conns = make(map[net.Conn]struct{})
+			mu.Unlock()
+			for i := 0; i < requests; i++ {
+				req, _ := http.NewRequestWithContext(context.Background(), http.MethodGet, srv.URL, http.NoBody)
+				resp, err := client.Do(req)
+				if err != nil {
+					b.Fatalf("do: %v", err)
+				}
+				if drain {
+					DrainClose(resp)
+				} else {
+					resp.Body.Close()
+				}
+			}
+			// close idle conns between passes so the bare client's per-pass
+			// sockets land in TIME_WAIT and free up before the next pass.
+			client.CloseIdleConnections()
+			mu.Lock()
+			lastPass = len(conns)
+			mu.Unlock()
+		}
+		b.StopTimer()
+
+		// distinct conns for a single pass of `requests`.
+		b.ReportMetric(float64(lastPass), "conns/op")
+	}
+
+	b.Run("tuned-drain", func(b *testing.B) {
+		resetBench()
+		tr, err := buildTransport("", 8)
+		if err != nil {
+			b.Fatalf("buildTransport: %v", err)
+		}
+		run(b, true, &http.Client{Timeout: 5 * time.Second, Transport: tr})
+	})
+
+	b.Run("bare-noDrain", func(b *testing.B) {
+		run(b, false, &http.Client{
+			Timeout:   5 * time.Second,
+			Transport: http.DefaultTransport.(*http.Transport).Clone(),
+		})
+	})
+}
+
+// resetBench clears the package transport without a *testing.T for benchmarks.
+func resetBench() {
+	mu.Lock()
+	configured = nil
+	mu.Unlock()
+}

internal/logger/logger.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
@@ -37,7 +37,7 @@ var defaultLogger = &Logger{
 // Init creates the log directory if it doesn't exist.
 func Init(dir string) error {
 	if _, err := os.Stat(dir); os.IsNotExist(err) {
-		if err = os.Mkdir(dir, 0755); err != nil {
+		if err := os.Mkdir(dir, 0o750); err != nil {
 			return err
 		}
 	}
@@ -62,7 +62,7 @@ func (l *Logger) getWriter(path string) (*bufio.Writer, error) {
 		return w, nil
 	}
 
-	f, err := os.OpenFile(path, os.O_CREATE|os.O_WRONLY|os.O_APPEND, 0666)
+	f, err := os.OpenFile(path, os.O_CREATE|os.O_WRONLY|os.O_APPEND, 0o600)
 	if err != nil {
 		return nil, err
 	}
@@ -124,7 +124,10 @@ func (l *Logger) Close() error {
 
 // CreateFile initializes a log file for the given URL and writes the header.
 func CreateFile(logFiles *[]string, url string, dir string) error {
-	sanitizedURL := strings.Split(url, "://")[1]
+	sanitizedURL := url
+	if _, after, ok := strings.Cut(url, "://"); ok {
+		sanitizedURL = after
+	}
 	path := filepath.Join(dir, sanitizedURL+".log")
 
 	header := fmt.Sprintf("       _____________\n__________(_)__  __/\n__  ___/_  /__  /_  \n_(__  )_  / _  __/  \n/____/ /_/  /_/    \n\nsif log file for %s\nhttps://sif.sh\n\n", url)

internal/logger/logger_test.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·

internal/modules/analytics_ui_exposure_test.go

@@ -0,0 +1,164 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runAnalyticsModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func analyticsExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestAnalyticsUIExposureModules(t *testing.T) {
+	const metabase = "../../modules/recon/metabase-api-exposure.yaml"
+	const zeppelin = "../../modules/recon/zeppelin-api-exposure.yaml"
+	const jupyter = "../../modules/recon/jupyter-api-exposure.yaml"
+
+	metabaseProps := `{"engines":{"postgres":{"driver-name":"PostgreSQL"}},` +
+		`"setup-token":"245f5f7c-8f0b-4c20-9a1e-6b2d7e1f0a33","anon-tracking-enabled":true,` +
+		`"available-locales":[["en","English"]],"password-complexity":{"total":6},` +
+		`"version":{"date":"2023-10-01","tag":"v0.47.2","branch":"release-x.47.x","hash":"abc1234"}}`
+
+	zeppelinVersion := `{"status":"OK","message":"Zeppelin version",` +
+		`"body":{"version":"0.10.1","git-commit-id":"a1b2c3d4e5","git-timestamp":"2022-01-15 10:00:00"}}`
+
+	jupyterStatus := `{"started":"2024-01-01T00:00:00.000000Z",` +
+		`"last_activity":"2024-01-01T01:23:45.000000Z","connections":2,"kernels":3}`
+
+	t.Run("an exposed metabase properties api is flagged and versioned", func(t *testing.T) {
+		res := runAnalyticsModule(t, metabase, 200, metabaseProps)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a metabase finding")
+		}
+		if v := analyticsExtract(res, "metabase_version"); v != "v0.47.2" {
+			t.Errorf("metabase_version=%q, want v0.47.2", v)
+		}
+	})
+
+	t.Run("an exposed zeppelin server is flagged and versioned", func(t *testing.T) {
+		res := runAnalyticsModule(t, zeppelin, 200, zeppelinVersion)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a zeppelin finding")
+		}
+		if v := analyticsExtract(res, "zeppelin_version"); v != "0.10.1" {
+			t.Errorf("zeppelin_version=%q, want 0.10.1", v)
+		}
+	})
+
+	t.Run("an exposed jupyter status api is flagged with the kernel count", func(t *testing.T) {
+		res := runAnalyticsModule(t, jupyter, 200, jupyterStatus)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a jupyter finding")
+		}
+		if v := analyticsExtract(res, "jupyter_active_kernels"); v != "3" {
+			t.Errorf("jupyter_active_kernels=%q, want 3", v)
+		}
+	})
+
+	t.Run("a live metabase token without the tracking setting is not flagged", func(t *testing.T) {
+		body := `{"setup-token":"245f5f7c-8f0b-4c20-9a1e-6b2d7e1f0a33","name":"app"}`
+		if res := runAnalyticsModule(t, metabase, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a setup token alone should not match metabase, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a metabase tracking setting without a setup token is not flagged", func(t *testing.T) {
+		body := `{"anon-tracking-enabled":true,"name":"app"}`
+		if res := runAnalyticsModule(t, metabase, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a tracking setting alone should not match metabase, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a patched metabase with a null setup token is not flagged", func(t *testing.T) {
+		body := `{"setup-token":null,"anon-tracking-enabled":true,` +
+			`"version":{"tag":"v0.47.2"}}`
+		if res := runAnalyticsModule(t, metabase, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a null setup token should not match metabase, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a zeppelin banner without a git commit id is not flagged", func(t *testing.T) {
+		body := `{"status":"OK","message":"Zeppelin version","body":{}}`
+		if res := runAnalyticsModule(t, zeppelin, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a banner alone should not match zeppelin, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a git commit id without the zeppelin banner is not flagged", func(t *testing.T) {
+		body := `{"git-commit-id":"a1b2c3d","name":"app"}`
+		if res := runAnalyticsModule(t, zeppelin, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a commit id alone should not match zeppelin, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a jupyter status without a kernels field is not flagged", func(t *testing.T) {
+		body := `{"started":"2024-01-01T00:00:00Z","last_activity":"2024-01-01T01:00:00Z","connections":2}`
+		if res := runAnalyticsModule(t, jupyter, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a status without kernels should not match jupyter, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a jupyter status without a connections field is not flagged", func(t *testing.T) {
+		body := `{"started":"2024-01-01T00:00:00Z","last_activity":"2024-01-01T01:00:00Z","kernels":3}`
+		if res := runAnalyticsModule(t, jupyter, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a status without connections should not match jupyter, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic version json is not an analytics service", func(t *testing.T) {
+		body := `{"version":"1.0.0","name":"app"}`
+		for _, file := range []string{metabase, zeppelin, jupyter} {
+			if res := runAnalyticsModule(t, file, 200, body); len(res.Findings) > 0 {
+				t.Errorf("%s: a generic version should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{metabase, zeppelin, jupyter} {
+			if res := runAnalyticsModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{metabase, zeppelin, jupyter} {
+			if res := runAnalyticsModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/app_config_exposure_test.go

@@ -0,0 +1,173 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runAppCfgModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func appCfgExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestAppConfigExposureModules(t *testing.T) {
+	const spring = "../../modules/recon/spring-application-config-exposure.yaml"
+	const appsettings = "../../modules/recon/appsettings-exposure.yaml"
+	const wpconfig = "../../modules/recon/wp-config-backup-exposure.yaml"
+
+	springProps := "spring.application.name=billing\n" +
+		"spring.datasource.url=jdbc:mysql://db.internal:3306/billing\n" +
+		"spring.datasource.username=app\nspring.datasource.password=s3cr3tP@ss\n" +
+		"spring.jpa.hibernate.ddl-auto=update\nserver.port=8080\n"
+
+	springYaml := "spring:\n  datasource:\n    url: jdbc:postgresql://pg.internal:5432/app\n" +
+		"    username: app\n    password: hunter2\nserver:\n  port: 8443\n"
+
+	appSettings := `{` + "\n" +
+		`  "Logging": { "LogLevel": { "Default": "Information" } },` + "\n" +
+		`  "ConnectionStrings": {` + "\n" +
+		`    "DefaultConnection": "Server=db;Database=app;User Id=sa;Password=P@ssw0rd;"` + "\n" +
+		`  },` + "\n" +
+		`  "AllowedHosts": "*"` + "\n}"
+
+	wpConfig := "<?php\ndefine( 'DB_NAME', 'wordpress' );\ndefine( 'DB_USER', 'wp' );\n" +
+		"define( 'DB_PASSWORD', 'Tr0ub4dor&3' );\ndefine( 'DB_HOST', 'localhost' );\n" +
+		"$table_prefix = 'wp_';\n"
+
+	t.Run("a spring properties file leaks the jdbc url", func(t *testing.T) {
+		res := runAppCfgModule(t, spring, 200, springProps)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a spring config finding")
+		}
+		if v := appCfgExtract(res, "jdbc_url"); v != "jdbc:mysql://db.internal:3306/billing" {
+			t.Errorf("jdbc_url=%q, want the mysql url", v)
+		}
+	})
+
+	t.Run("a spring yaml file also matches and names the jdbc url", func(t *testing.T) {
+		res := runAppCfgModule(t, spring, 200, springYaml)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a spring config finding for yaml")
+		}
+		if v := appCfgExtract(res, "jdbc_url"); v != "jdbc:postgresql://pg.internal:5432/app" {
+			t.Errorf("jdbc_url=%q, want the postgres url", v)
+		}
+	})
+
+	t.Run("an appsettings json leaks the connection string", func(t *testing.T) {
+		res := runAppCfgModule(t, appsettings, 200, appSettings)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an appsettings finding")
+		}
+		want := "Server=db;Database=app;User Id=sa;Password=P@ssw0rd;"
+		if v := appCfgExtract(res, "connection_string"); v != want {
+			t.Errorf("connection_string=%q, want %q", v, want)
+		}
+	})
+
+	t.Run("a wp-config backup leaks the database password", func(t *testing.T) {
+		res := runAppCfgModule(t, wpconfig, 200, wpConfig)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a wp-config finding")
+		}
+		if v := appCfgExtract(res, "db_password"); v != "Tr0ub4dor&3" {
+			t.Errorf("db_password=%q, want Tr0ub4dor&3", v)
+		}
+	})
+
+	t.Run("a spring config with no credential is not flagged", func(t *testing.T) {
+		body := "spring.application.name=app\nserver.port=8080\n"
+		if res := runAppCfgModule(t, spring, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a credential-free config should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a spring config inside an html page is not flagged", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>spring.datasource.password=x</pre></body></html>"
+		if res := runAppCfgModule(t, spring, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an appsettings without a connection string is not flagged", func(t *testing.T) {
+		body := `{"Logging":{"LogLevel":{"Default":"Information"}},"AllowedHosts":"*"}`
+		if res := runAppCfgModule(t, appsettings, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a config without a connection string should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an appsettings with no password is not a credential leak", func(t *testing.T) {
+		body := `{"ConnectionStrings":{"Db":"Server=db;Database=app;Integrated Security=true;"}}`
+		if res := runAppCfgModule(t, appsettings, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a passwordless connection string should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an appsettings password outside a connection strings section is not flagged", func(t *testing.T) {
+		body := `{"Smtp":{"Host":"Server=mail;Password=relaypass;"}}`
+		if res := runAppCfgModule(t, appsettings, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a password outside ConnectionStrings should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("prose that names the wp-config password is not a backup", func(t *testing.T) {
+		body := "set the DB_PASSWORD env var before running the installer"
+		if res := runAppCfgModule(t, wpconfig, 200, body); len(res.Findings) > 0 {
+			t.Errorf("prose naming DB_PASSWORD should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a wp-config shown in an html page is not flagged", func(t *testing.T) {
+		body := "<html><head><title>setup</title></head><body>define( 'DB_PASSWORD', 'x' ); DB_NAME</body></html>"
+		if res := runAppCfgModule(t, wpconfig, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{spring, appsettings, wpconfig} {
+			if res := runAppCfgModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{spring, appsettings, wpconfig} {
+			if res := runAppCfgModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/argocd_exposure_test.go

@@ -0,0 +1,92 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runArgocdModule(t *testing.T, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule("../../modules/recon/argocd-api-exposure.yaml")
+	if err != nil {
+		t.Fatalf("parse argocd module: %v", err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute argocd module: %v", err)
+	}
+	return res
+}
+
+func argocdExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestArgocdExposureModule(t *testing.T) {
+	argocdVersion := `{"Version":"v2.9.3+a1b2c3d","BuildDate":"2024-01-15T12:00:00Z","GitCommit":"a1b2c3d",` +
+		`"GitTreeState":"clean","GoVersion":"go1.21.5","Compiler":"gc","Platform":"linux/amd64",` +
+		`"KustomizeVersion":"v5.2.1 2023-10-19","HelmVersion":"v3.13.2+gadc03ef",` +
+		`"KubectlVersion":"v0.26.11","JsonnetVersion":"v0.20.0"}`
+
+	t.Run("an exposed argocd version endpoint is flagged and versioned", func(t *testing.T) {
+		res := runArgocdModule(t, 200, argocdVersion)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an argocd finding")
+		}
+		if v := argocdExtract(res, "argocd_version"); v != "v2.9.3+a1b2c3d" {
+			t.Errorf("argocd_version=%q, want v2.9.3+a1b2c3d", v)
+		}
+	})
+
+	t.Run("an argocd kustomize version without a helm version is not flagged", func(t *testing.T) {
+		body := `{"Version":"v2.9.3","KustomizeVersion":"v5.2.1 2023-10-19"}`
+		if res := runArgocdModule(t, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a kustomize version alone should not match argocd, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an argocd helm version without a kustomize version is not flagged", func(t *testing.T) {
+		body := `{"Version":"v2.9.3","HelmVersion":"v3.13.2+gadc03ef"}`
+		if res := runArgocdModule(t, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a helm version alone should not match argocd, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic version endpoint is not argocd", func(t *testing.T) {
+		body := `{"Version":"v1.0.0","GitCommit":"abc"}`
+		if res := runArgocdModule(t, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic version json should not match argocd, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		if res := runArgocdModule(t, 200, "ok"); len(res.Findings) > 0 {
+			t.Errorf("a plain 200 body should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		if res := runArgocdModule(t, 404, "not found"); len(res.Findings) > 0 {
+			t.Errorf("a 404 should not match, got %d findings", len(res.Findings))
+		}
+	})
+}

internal/modules/attack_modes_test.go

@@ -0,0 +1,148 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"reflect"
+	"sort"
+	"sync"
+	"testing"
+
+	"github.com/dropalldatabases/sif/internal/httpx"
+)
+
+func reqURLs(reqs []*httpRequest) []string {
+	urls := make([]string, len(reqs))
+	for i, r := range reqs {
+		urls[i] = r.URL
+	}
+	sort.Strings(urls)
+	return urls
+}
+
+func TestGenerateHTTPRequestsAttack(t *testing.T) {
+	const target = "http://t"
+	paths2 := []string{"{{BaseURL}}/a?x={{payload}}", "{{BaseURL}}/b?x={{payload}}"}
+	pay2 := []string{"1", "2"}
+	cross := []string{"http://t/a?x=1", "http://t/a?x=2", "http://t/b?x=1", "http://t/b?x=2"}
+	paired := []string{"http://t/a?x=1", "http://t/b?x=2"}
+
+	tests := []struct {
+		name     string
+		paths    []string
+		payloads []string
+		attack   string
+		want     []string
+	}{
+		{"clusterbomb default crosses all", paths2, pay2, "", cross},
+		{"clusterbomb explicit crosses all", paths2, pay2, "clusterbomb", cross},
+		{"pitchfork pairs by index", paths2, pay2, "pitchfork", paired},
+		{"pitchfork stops at fewer payloads", append(paths2, "{{BaseURL}}/c?x={{payload}}"), pay2, "pitchfork", paired},
+		{"pitchfork stops at fewer paths", paths2, []string{"1", "2", "3"}, "pitchfork", paired},
+		{"attack is case insensitive", paths2, pay2, "Pitchfork", paired},
+		{"no payloads ignores attack", []string{"{{BaseURL}}/a", "{{BaseURL}}/b"}, nil, "pitchfork", []string{"http://t/a", "http://t/b"}},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			cfg := &HTTPConfig{Paths: tt.paths, Payloads: tt.payloads, Attack: tt.attack}
+			reqs, err := generateHTTPRequests(target, cfg)
+			if err != nil {
+				t.Fatalf("generateHTTPRequests: %v", err)
+			}
+			got := reqURLs(reqs)
+			want := append([]string(nil), tt.want...)
+			sort.Strings(want)
+			if !reflect.DeepEqual(got, want) {
+				t.Errorf("attack %q:\n got %v\nwant %v", tt.attack, got, want)
+			}
+		})
+	}
+}
+
+func TestValidateAttack(t *testing.T) {
+	for _, ok := range []string{"", "clusterbomb", "pitchfork", "Pitchfork", "CLUSTERBOMB"} {
+		if err := validateAttack(ok); err != nil {
+			t.Errorf("validateAttack(%q) = %v, want nil", ok, err)
+		}
+	}
+	for _, bad := range []string{"sniper", "batteringram", "bogus"} {
+		if err := validateAttack(bad); err == nil {
+			t.Errorf("validateAttack(%q) = nil, want error", bad)
+		}
+	}
+}
+
+func TestParseAttackValidation(t *testing.T) {
+	dir := t.TempDir()
+	write := func(name, body string) string {
+		p := filepath.Join(dir, name)
+		if err := os.WriteFile(p, []byte(body), 0o644); err != nil {
+			t.Fatal(err)
+		}
+		return p
+	}
+
+	good := write("good.yaml", "id: ok\ntype: http\nhttp:\n  attack: pitchfork\n  paths: [\"{{BaseURL}}/\"]\n")
+	if _, err := ParseYAMLModule(good); err != nil {
+		t.Fatalf("valid attack rejected: %v", err)
+	}
+
+	bad := write("bad.yaml", "id: bad\ntype: http\nhttp:\n  attack: sniper\n  paths: [\"{{BaseURL}}/\"]\n")
+	if _, err := ParseYAMLModule(bad); err == nil {
+		t.Fatal("invalid attack accepted")
+	}
+}
+
+// TestExecuteHTTPModulePitchfork drives the executor end to end and confirms
+// pitchfork only fires the index-paired requests, not the full cross product.
+func TestExecuteHTTPModulePitchfork(t *testing.T) {
+	var mu sync.Mutex
+	var hits []string
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		mu.Lock()
+		hits = append(hits, r.URL.Path+"?"+r.URL.RawQuery)
+		mu.Unlock()
+		_, _ = w.Write([]byte("ok"))
+	}))
+	defer srv.Close()
+
+	def := &YAMLModule{
+		ID:   "pf",
+		Type: TypeHTTP,
+		HTTP: &HTTPConfig{
+			Attack:   "pitchfork",
+			Paths:    []string{"{{BaseURL}}/a?x={{payload}}", "{{BaseURL}}/b?x={{payload}}"},
+			Payloads: []string{"1", "2"},
+			Matchers: []Matcher{{Type: "word", Part: "body", Words: []string{"ok"}}},
+		},
+	}
+
+	opts := Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)}
+	if _, err := ExecuteHTTPModule(context.Background(), srv.URL, def, opts); err != nil {
+		t.Fatalf("ExecuteHTTPModule: %v", err)
+	}
+
+	mu.Lock()
+	got := append([]string(nil), hits...)
+	mu.Unlock()
+	sort.Strings(got)
+	want := []string{"/a?x=1", "/b?x=2"}
+	if !reflect.DeepEqual(got, want) {
+		t.Errorf("pitchfork hit %v, want %v (clusterbomb would also hit /a?x=2 and /b?x=1)", got, want)
+	}
+}

internal/modules/bigdata_api_exposure_test.go

@@ -0,0 +1,156 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runBigDataModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func bigDataExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestBigDataAPIExposureModules(t *testing.T) {
+	const solr = "../../modules/recon/solr-api-exposure.yaml"
+	const spark = "../../modules/recon/spark-api-exposure.yaml"
+	const hadoop = "../../modules/recon/hadoop-yarn-api-exposure.yaml"
+
+	solrSystem := `{"responseHeader":{"status":0,"QTime":15},"mode":"std",` +
+		`"solr_home":"/var/solr/data","lucene":{"solr-spec-version":"9.4.0",` +
+		`"solr-impl-version":"9.4.0","lucene-spec-version":"9.8.0","lucene-impl-version":"9.8.0"},` +
+		`"jvm":{"version":"17.0.9"}}`
+
+	sparkState := `{"url":"spark://master:7077","workers":[{"id":"worker-1","host":"10.0.0.5"}],` +
+		`"aliveworkers":2,"cores":8,"coresused":0,"memory":15360,"activeapps":[],` +
+		`"completedapps":[],"status":"ALIVE"}`
+
+	hadoopInfo := `{"clusterInfo":{"id":1700000000000,"startedOn":1700000000000,"state":"STARTED",` +
+		`"haState":"ACTIVE","resourceManagerVersion":"3.3.6","resourceManagerBuildVersion":"3.3.6 from abc",` +
+		`"hadoopVersion":"3.3.6","hadoopBuildVersion":"3.3.6 from abc","hadoopVersionBuiltOn":"2023-06-18"}}`
+
+	t.Run("an exposed solr admin api is flagged and versioned", func(t *testing.T) {
+		res := runBigDataModule(t, solr, 200, solrSystem)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a solr finding")
+		}
+		if v := bigDataExtract(res, "solr_version"); v != "9.4.0" {
+			t.Errorf("solr_version=%q, want 9.4.0", v)
+		}
+	})
+
+	t.Run("an exposed spark master leaks its url", func(t *testing.T) {
+		res := runBigDataModule(t, spark, 200, sparkState)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a spark finding")
+		}
+		if v := bigDataExtract(res, "spark_master_url"); v != "spark://master:7077" {
+			t.Errorf("spark_master_url=%q, want spark://master:7077", v)
+		}
+	})
+
+	t.Run("an exposed hadoop yarn api is flagged and versioned", func(t *testing.T) {
+		res := runBigDataModule(t, hadoop, 200, hadoopInfo)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a hadoop finding")
+		}
+		if v := bigDataExtract(res, "hadoop_version"); v != "3.3.6" {
+			t.Errorf("hadoop_version=%q, want 3.3.6", v)
+		}
+	})
+
+	t.Run("a solr spec version without a solr home is not solr", func(t *testing.T) {
+		body := `{"lucene":{"solr-spec-version":"9.4.0"},"name":"otherservice"}`
+		if res := runBigDataModule(t, solr, 200, body); len(res.Findings) > 0 {
+			t.Errorf("spec version alone should not match solr, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a solr home without a spec version is not solr", func(t *testing.T) {
+		body := `{"solr_home":"/var/solr/data","mode":"std"}`
+		if res := runBigDataModule(t, solr, 200, body); len(res.Findings) > 0 {
+			t.Errorf("solr home alone should not match solr, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a spark url without alive workers is not flagged", func(t *testing.T) {
+		body := `{"url":"spark://master:7077","workers":[],"status":"ALIVE"}`
+		if res := runBigDataModule(t, spark, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a spark url alone should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("alive workers behind a non spark url is not flagged", func(t *testing.T) {
+		body := `{"url":"http://internal:8080","aliveworkers":2}`
+		if res := runBigDataModule(t, spark, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a non spark url should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a cluster info without a resource manager version is not hadoop", func(t *testing.T) {
+		body := `{"clusterInfo":{"id":1,"state":"STARTED","hadoopVersion":"3.3.6"}}`
+		if res := runBigDataModule(t, hadoop, 200, body); len(res.Findings) > 0 {
+			t.Errorf("cluster info alone should not match hadoop, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a resource manager version without a cluster info is not hadoop", func(t *testing.T) {
+		body := `{"resourceManagerVersion":"3.3.6","app":"custom"}`
+		if res := runBigDataModule(t, hadoop, 200, body); len(res.Findings) > 0 {
+			t.Errorf("rm version alone should not match hadoop, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic json endpoint is not a spark master", func(t *testing.T) {
+		body := `{"url":"http://app","workers":5,"name":"myservice"}`
+		if res := runBigDataModule(t, spark, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic json should not match spark, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{solr, spark, hadoop} {
+			if res := runBigDataModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{solr, spark, hadoop} {
+			if res := runBigDataModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/buildtool_credential_exposure_test.go

@@ -0,0 +1,198 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runBuildCredModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func buildCredExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestBuildToolCredentialExposureModules(t *testing.T) {
+	const maven = "../../modules/recon/maven-settings-exposure.yaml"
+	const gradle = "../../modules/recon/gradle-properties-exposure.yaml"
+	const nuget = "../../modules/recon/nuget-config-exposure.yaml"
+
+	mavenSettings := "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
+		"<settings xmlns=\"http://maven.apache.org/SETTINGS/1.0.0\">\n" +
+		"  <servers>\n    <server>\n      <id>nexus-releases</id>\n" +
+		"      <username>deploy</username>\n      <password>S3cretDeployPass</password>\n" +
+		"    </server>\n  </servers>\n</settings>\n"
+
+	gradleProps := "org.gradle.jvmargs=-Xmx2g\nossrhUsername=deployer\n" +
+		"ossrhPassword=mySonatypeSecret\nsigning.password=mySigningSecret\n"
+
+	nugetConfig := "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<configuration>\n" +
+		"  <packageSourceCredentials>\n    <MyFeed>\n" +
+		"      <add key=\"Username\" value=\"deploy\" />\n" +
+		"      <add key=\"ClearTextPassword\" value=\"S3cretFeedPass\" />\n" +
+		"    </MyFeed>\n  </packageSourceCredentials>\n</configuration>\n"
+
+	t.Run("an exposed maven settings leaks the server username", func(t *testing.T) {
+		res := runBuildCredModule(t, maven, 200, mavenSettings)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a maven finding")
+		}
+		if v := buildCredExtract(res, "maven_username"); v != "deploy" {
+			t.Errorf("maven_username=%q, want deploy", v)
+		}
+	})
+
+	t.Run("an exposed gradle properties leaks the secret property", func(t *testing.T) {
+		res := runBuildCredModule(t, gradle, 200, gradleProps)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a gradle finding")
+		}
+		if v := buildCredExtract(res, "gradle_secret_property"); v != "ossrhPassword" {
+			t.Errorf("gradle_secret_property=%q, want ossrhPassword", v)
+		}
+	})
+
+	t.Run("an exposed nuget config leaks the feed username", func(t *testing.T) {
+		res := runBuildCredModule(t, nuget, 200, nugetConfig)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a nuget finding")
+		}
+		if v := buildCredExtract(res, "nuget_username"); v != "deploy" {
+			t.Errorf("nuget_username=%q, want deploy", v)
+		}
+	})
+
+	t.Run("a maven settings with mirrors but no password is not flagged", func(t *testing.T) {
+		body := "<settings>\n  <mirrors>\n    <mirror>\n      <id>central</id>\n" +
+			"      <url>https://repo.example.com/maven2</url>\n    </mirror>\n  </mirrors>\n</settings>\n"
+		if res := runBuildCredModule(t, maven, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a settings without a password should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a maven settings is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre><settings><server><password>x</password></server></settings></pre></body></html>"
+		if res := runBuildCredModule(t, maven, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html maven tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a gradle properties with no credential property is not flagged", func(t *testing.T) {
+		body := "org.gradle.jvmargs=-Xmx2g\nversion=1.0.0\norg.gradle.daemon=true\n"
+		if res := runBuildCredModule(t, gradle, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a non credential properties file should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a comment naming a password is not a credential property", func(t *testing.T) {
+		body := "# set your password=here before building\norg.gradle.daemon=true\n"
+		if res := runBuildCredModule(t, gradle, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a comment line should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an empty password property is not flagged", func(t *testing.T) {
+		body := "signing.password=\nsigning.keyId=24875D73\n"
+		if res := runBuildCredModule(t, gradle, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an empty value should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a gradle property is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html>\n<html><body><pre>\nossrhPassword=mySonatypeSecret\n</pre></body></html>\n"
+		if res := runBuildCredModule(t, gradle, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html gradle tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a nuget config without a credentials section is not flagged", func(t *testing.T) {
+		body := "<configuration>\n  <packageSources>\n" +
+			"    <add key=\"nuget.org\" value=\"https://api.nuget.org/v3/index.json\" />\n" +
+			"  </packageSources>\n</configuration>\n"
+		if res := runBuildCredModule(t, nuget, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a config without credentials should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a nuget credentials section without a password is not flagged", func(t *testing.T) {
+		body := "<configuration>\n  <packageSourceCredentials>\n    <MyFeed>\n" +
+			"      <add key=\"Username\" value=\"deploy\" />\n" +
+			"    </MyFeed>\n  </packageSourceCredentials>\n</configuration>\n"
+		if res := runBuildCredModule(t, nuget, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a credentials section without a password should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an appsettings password is not a nuget feed credential", func(t *testing.T) {
+		body := "<configuration>\n  <appSettings>\n" +
+			"    <add key=\"Password\" value=\"appsecret\" />\n" +
+			"  </appSettings>\n</configuration>\n"
+		if res := runBuildCredModule(t, nuget, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an appsettings password should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a nuget config is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre><packageSourceCredentials><add key=\"ClearTextPassword\" value=\"x\" /></packageSourceCredentials></pre></body></html>"
+		if res := runBuildCredModule(t, nuget, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html nuget tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{maven, gradle, nuget} {
+			if res := runBuildCredModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{maven, gradle, nuget} {
+			if res := runBuildCredModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/cms_config_exposure_test.go

@@ -0,0 +1,205 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runCMSCfgModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func cmsCfgExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestCMSConfigExposureModules(t *testing.T) {
+	const joomla = "../../modules/recon/joomla-config-exposure.yaml"
+	const drupal = "../../modules/recon/drupal-config-exposure.yaml"
+	const magento = "../../modules/recon/magento-config-exposure.yaml"
+
+	joomlaConfig := "<?php\nclass JConfig {\n\tpublic $offline = '0';\n" +
+		"\tpublic $host = 'localhost';\n\tpublic $user = 'joomla_user';\n" +
+		"\tpublic $password = 'S3cretJoomlaPass';\n\tpublic $db = 'joomla_db';\n" +
+		"\tpublic $dbprefix = 'jos_';\n\tpublic $secret = 'AbCdEfGhIjKlMnOp';\n}\n"
+
+	drupalConfig := "<?php\n$databases['default']['default'] = array (\n" +
+		"  'database' => 'drupal_db',\n  'username' => 'drupal_user',\n" +
+		"  'password' => 'S3cretDrupalPass',\n  'host' => 'localhost',\n" +
+		"  'driver' => 'mysql',\n);\n$settings['hash_salt'] = 'longrandomhashsalt';\n"
+
+	magentoConfig := "<?php\nreturn [\n  'backend' => ['frontName' => 'admin_x7y'],\n" +
+		"  'crypt' => ['key' => 'a1b2c3d4e5f6g7h8'],\n  'db' => [\n" +
+		"    'connection' => ['default' => [\n      'host' => 'localhost',\n" +
+		"      'dbname' => 'magento',\n      'username' => 'magento_user',\n" +
+		"      'password' => 'S3cretMagentoPass',\n    ]],\n  ],\n  'MAGE_MODE' => 'production',\n];\n"
+
+	t.Run("an exposed joomla configuration leaks the password", func(t *testing.T) {
+		res := runCMSCfgModule(t, joomla, 200, joomlaConfig)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a joomla finding")
+		}
+		if v := cmsCfgExtract(res, "joomla_password"); v != "S3cretJoomlaPass" {
+			t.Errorf("joomla_password=%q, want S3cretJoomlaPass", v)
+		}
+	})
+
+	t.Run("an exposed drupal settings leaks the password", func(t *testing.T) {
+		res := runCMSCfgModule(t, drupal, 200, drupalConfig)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a drupal finding")
+		}
+		if v := cmsCfgExtract(res, "drupal_password"); v != "S3cretDrupalPass" {
+			t.Errorf("drupal_password=%q, want S3cretDrupalPass", v)
+		}
+	})
+
+	t.Run("an exposed magento env leaks the crypt key", func(t *testing.T) {
+		res := runCMSCfgModule(t, magento, 200, magentoConfig)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a magento finding")
+		}
+		if v := cmsCfgExtract(res, "magento_crypt_key"); v != "a1b2c3d4e5f6g7h8" {
+			t.Errorf("magento_crypt_key=%q, want a1b2c3d4e5f6g7h8", v)
+		}
+	})
+
+	t.Run("a joomla config missing the password is not flagged", func(t *testing.T) {
+		body := "<?php\nclass JConfig {\n\tpublic $host = 'localhost';\n" +
+			"\tpublic $db = 'joomla_db';\n\tpublic $dbprefix = 'jos_';\n}\n"
+		if res := runCMSCfgModule(t, joomla, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a config without a password should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a php class with a public password but no jconfig is not joomla", func(t *testing.T) {
+		body := "<?php\nclass MyAuth {\n\tpublic $password = 'changeme';\n" +
+			"\tpublic $username = 'admin';\n}\n"
+		if res := runCMSCfgModule(t, joomla, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic class should not match joomla, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a php array with a password but no databases is not drupal", func(t *testing.T) {
+		body := "<?php\n$config = array('password' => 'x', 'host' => 'y');\n"
+		if res := runCMSCfgModule(t, drupal, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic array should not match drupal, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a drupal databases array without a password is not flagged", func(t *testing.T) {
+		body := "<?php\n$databases['default']['default'] = array (\n" +
+			"  'database' => 'drupal_db',\n  'host' => 'localhost',\n  'driver' => 'mysql',\n);\n"
+		if res := runCMSCfgModule(t, drupal, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a databases array without a password should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a php return array with a password but no magento markers is not flagged", func(t *testing.T) {
+		body := "<?php\nreturn ['db' => ['password' => 'secret', 'host' => 'localhost']];\n"
+		if res := runCMSCfgModule(t, magento, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic return array should not match magento, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a magento config without a credential is not flagged", func(t *testing.T) {
+		body := "<?php\nreturn ['MAGE_MODE' => 'production', 'db' => ['host' => 'localhost']];\n"
+		if res := runCMSCfgModule(t, magento, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a magento config without a credential should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a joomla config is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>class JConfig { public $password = 'x'; public $db = 'y'; }</pre></body></html>"
+		if res := runCMSCfgModule(t, joomla, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html joomla tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a drupal settings using env indirection is not a literal password leak", func(t *testing.T) {
+		body := "<?php\n$databases['default']['default'] = array (\n" +
+			"  'database' => 'drupal_db',\n  'username' => 'drupal_user',\n" +
+			"  'password' => getenv('DB_PASS'),\n  'host' => 'localhost',\n);\n"
+		if res := runCMSCfgModule(t, drupal, 200, body); len(res.Findings) > 0 {
+			t.Errorf("env indirection should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a magento env with a cloud placeholder key is not a literal leak", func(t *testing.T) {
+		body := "<?php\nreturn ['crypt' => ['key' => '#env.CRYPT_KEY#'], 'MAGE_MODE' => 'production'];\n"
+		if res := runCMSCfgModule(t, magento, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a cloud placeholder should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a magento env with a placeholder key but a literal password is flagged not mis-extracted", func(t *testing.T) {
+		body := "<?php\nreturn ['crypt' => ['key' => '#env.CRYPT_KEY#'],\n" +
+			"  'db' => ['connection' => ['default' => ['password' => 'RealDbPass']]],\n" +
+			"  'MAGE_MODE' => 'production'];\n"
+		res := runCMSCfgModule(t, magento, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a magento finding on the literal password")
+		}
+		if v := cmsCfgExtract(res, "magento_crypt_key"); v == "#env.CRYPT_KEY#" {
+			t.Errorf("extractor surfaced the placeholder %q as the crypt key", v)
+		}
+	})
+
+	t.Run("an html page demonstrating a drupal config is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>$databases['default']['default'] = array('password' => 'x');</pre></body></html>"
+		if res := runCMSCfgModule(t, drupal, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html drupal tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a magento config is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>'crypt' => ['key' => 'x'], 'MAGE_MODE' => 'production'</pre></body></html>"
+		if res := runCMSCfgModule(t, magento, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html magento tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{joomla, drupal, magento} {
+			if res := runCMSCfgModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{joomla, drupal, magento} {
+			if res := runCMSCfgModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/credential_exposure_test.go

@@ -0,0 +1,113 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runCredModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func credExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestCredentialExposureModules(t *testing.T) {
+	const aws = "../../modules/recon/aws-credentials-exposure.yaml"
+	const npmrc = "../../modules/recon/npmrc-exposure.yaml"
+	const docker = "../../modules/recon/docker-config-exposure.yaml"
+
+	t.Run("aws credentials leak the access key id", func(t *testing.T) {
+		body := "[default]\naws_access_key_id = AKIAIOSFODNN7EXAMPLE\n" +
+			"aws_secret_access_key = wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY\n"
+		res := runCredModule(t, aws, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an aws credentials finding")
+		}
+		if v := credExtract(res, "aws_access_key_id"); v != "AKIAIOSFODNN7EXAMPLE" {
+			t.Errorf("aws_access_key_id=%q, want AKIAIOSFODNN7EXAMPLE", v)
+		}
+	})
+
+	t.Run("npmrc leaks the registry of an auth token", func(t *testing.T) {
+		body := "//registry.npmjs.org/:_authToken=npm_AbCdEf0123456789AbCdEf0123456789\n"
+		res := runCredModule(t, npmrc, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an npmrc finding")
+		}
+		if v := credExtract(res, "npm_registry"); v != "registry.npmjs.org" {
+			t.Errorf("npm_registry=%q, want registry.npmjs.org", v)
+		}
+	})
+
+	t.Run("docker config leaks the registry host", func(t *testing.T) {
+		body := `{"auths":{"registry.example.com":{"auth":"dXNlcm5hbWU6c3VwZXJzZWNyZXRwYXNz"}}}`
+		res := runCredModule(t, docker, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a docker config finding")
+		}
+		if v := credExtract(res, "docker_registry"); v != "registry.example.com" {
+			t.Errorf("docker_registry=%q, want registry.example.com", v)
+		}
+	})
+
+	t.Run("html page mentioning the key name is not a leak", func(t *testing.T) {
+		body := `<html><head><title>Docs</title></head><body>` +
+			`set your aws_secret_access_key in ~/.aws/credentials</body></html>`
+		if res := runCredModule(t, aws, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html doc mentioning the key should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{aws, npmrc, docker} {
+			if res := runCredModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{aws, npmrc, docker} {
+			if res := runCredModule(t, file, 200, "nothing to see here"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a docker auth field holding a jwt is not a leak", func(t *testing.T) {
+		body := `{"token":"x","auth":"eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxMjMifQ.SflKxwRJSMeKKF2QT4fwpMeJf36POk6yJV_adQssw5c"}`
+		if res := runCredModule(t, docker, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a jwt in an auth field should not match, got %d findings", len(res.Findings))
+		}
+	})
+}

internal/modules/data_pipeline_api_exposure_test.go

@@ -0,0 +1,151 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runPipelineModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func pipelineExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestDataPipelineAPIExposureModules(t *testing.T) {
+	const airflow = "../../modules/recon/airflow-api-exposure.yaml"
+	const flink = "../../modules/recon/flink-api-exposure.yaml"
+	const kafka = "../../modules/recon/kafka-connect-api-exposure.yaml"
+
+	airflowHealth := `{"metadatabase":{"status":"healthy"},"scheduler":{"status":"healthy",` +
+		`"latest_scheduler_heartbeat":"2023-09-13T09:35:49.123456+00:00"}}`
+
+	flinkOverview := `{"taskmanagers":1,"slots-total":4,"slots-available":4,"jobs-running":0,` +
+		`"jobs-finished":2,"jobs-cancelled":0,"jobs-failed":0,"flink-version":"1.17.1","flink-commit":"2750d5c"}`
+
+	kafkaConnect := `{"version":"3.5.0","commit":"c97b88d5db4de28d","kafka_cluster_id":"M_oad8FjQ1eMShri6_jjQg"}`
+
+	t.Run("an exposed airflow health endpoint is flagged", func(t *testing.T) {
+		res := runPipelineModule(t, airflow, 200, airflowHealth)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an airflow finding")
+		}
+		if v := pipelineExtract(res, "airflow_scheduler_heartbeat"); v != "2023-09-13T09:35:49.123456+00:00" {
+			t.Errorf("airflow_scheduler_heartbeat=%q, want the heartbeat timestamp", v)
+		}
+	})
+
+	t.Run("an exposed flink dashboard is flagged and versioned", func(t *testing.T) {
+		res := runPipelineModule(t, flink, 200, flinkOverview)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a flink finding")
+		}
+		if v := pipelineExtract(res, "flink_version"); v != "1.17.1" {
+			t.Errorf("flink_version=%q, want 1.17.1", v)
+		}
+	})
+
+	t.Run("an exposed kafka connect api is flagged and versioned", func(t *testing.T) {
+		res := runPipelineModule(t, kafka, 200, kafkaConnect)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a kafka connect finding")
+		}
+		if v := pipelineExtract(res, "kafka_version"); v != "3.5.0" {
+			t.Errorf("kafka_version=%q, want 3.5.0", v)
+		}
+	})
+
+	t.Run("an airflow metadatabase without a scheduler is not flagged", func(t *testing.T) {
+		body := `{"metadatabase":{"status":"healthy"}}`
+		if res := runPipelineModule(t, airflow, 200, body); len(res.Findings) > 0 {
+			t.Errorf("metadatabase alone should not match airflow, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an airflow scheduler without a metadatabase is not flagged", func(t *testing.T) {
+		body := `{"scheduler":{"status":"healthy","latest_scheduler_heartbeat":"2023-09-13T09:35:49.123456+00:00"}}`
+		if res := runPipelineModule(t, airflow, 200, body); len(res.Findings) > 0 {
+			t.Errorf("scheduler alone should not match airflow, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a flink version without a slot total is not flagged", func(t *testing.T) {
+		body := `{"flink-version":"1.17.1","taskmanagers":1}`
+		if res := runPipelineModule(t, flink, 200, body); len(res.Findings) > 0 {
+			t.Errorf("flink version alone should not match flink, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a slot total without a flink version is not flagged", func(t *testing.T) {
+		body := `{"slots-total":4,"jobs-running":0}`
+		if res := runPipelineModule(t, flink, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a slot total alone should not match flink, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a kafka cluster id without a version is not flagged", func(t *testing.T) {
+		body := `{"kafka_cluster_id":"M_oad8FjQ1eMShri6_jjQg","commit":"abc"}`
+		if res := runPipelineModule(t, kafka, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a cluster id alone should not match kafka connect, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a version without a kafka cluster id is not flagged", func(t *testing.T) {
+		body := `{"version":"3.5.0","name":"someservice"}`
+		if res := runPipelineModule(t, kafka, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a version alone should not match kafka connect, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic health json is not airflow", func(t *testing.T) {
+		body := `{"status":"UP","components":{"db":{"status":"UP"}}}`
+		if res := runPipelineModule(t, airflow, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic health should not match airflow, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{airflow, flink, kafka} {
+			if res := runPipelineModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{airflow, flink, kafka} {
+			if res := runPipelineModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/database_file_exposure_test.go

@@ -0,0 +1,166 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runDBFileModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func dbFileExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestDatabaseFileExposureModules(t *testing.T) {
+	const sqlDump = "../../modules/recon/sql-dump-exposure.yaml"
+	const sqlite = "../../modules/recon/sqlite-database-exposure.yaml"
+	const redis = "../../modules/recon/redis-dump-exposure.yaml"
+
+	mysqldump := "-- MySQL dump 10.13  Distrib 8.0.32, for Linux (x86_64)\n--\n" +
+		"-- Host: localhost    Database: appdb\n--\n-- Server version\t8.0.32\n\n" +
+		"DROP TABLE IF EXISTS `users`;\nCREATE TABLE `users` (\n" +
+		"  `id` int NOT NULL AUTO_INCREMENT,\n  `email` varchar(255) DEFAULT NULL,\n" +
+		"  PRIMARY KEY (`id`)\n) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;\n" +
+		"INSERT INTO `users` VALUES (1,'admin@x.com');\n"
+
+	pgdump := "--\n-- PostgreSQL database dump\n--\n\nSET statement_timeout = 0;\n" +
+		"CREATE TABLE public.accounts (\n    id integer NOT NULL,\n    email text\n);\n" +
+		"COPY public.accounts (id, email) FROM stdin;\n1\tadmin@x.com\n\\.\n"
+
+	sqliteFile := "SQLite format 3\x00" + strings.Repeat("\x00", 84) +
+		"\x05\x00CREATE TABLE users(id INTEGER PRIMARY KEY, email TEXT, password TEXT)\x00"
+
+	redisDump := "REDIS0011\xfa\x09redis-ver\x055.0.7\xfa\x0aredis-bits\xc0@\xfe\x00\xfb\x02\x00" +
+		"\x03key\x05value\xff\x00\x00\x00\x00\x00\x00\x00\x00"
+
+	t.Run("a mysqldump leaks the dumped table", func(t *testing.T) {
+		res := runDBFileModule(t, sqlDump, 200, mysqldump)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a sql dump finding")
+		}
+		if v := dbFileExtract(res, "dump_table"); v != "users" {
+			t.Errorf("dump_table=%q, want users", v)
+		}
+	})
+
+	t.Run("a postgresql dump also matches and names its table", func(t *testing.T) {
+		res := runDBFileModule(t, sqlDump, 200, pgdump)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a sql dump finding for pg_dump")
+		}
+		if v := dbFileExtract(res, "dump_table"); v != "accounts" {
+			t.Errorf("dump_table=%q, want accounts", v)
+		}
+	})
+
+	t.Run("a sqlite database file leaks its schema table", func(t *testing.T) {
+		res := runDBFileModule(t, sqlite, 200, sqliteFile)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a sqlite finding")
+		}
+		if v := dbFileExtract(res, "table_name"); v != "users" {
+			t.Errorf("table_name=%q, want users", v)
+		}
+	})
+
+	t.Run("a redis rdb snapshot leaks its format version", func(t *testing.T) {
+		res := runDBFileModule(t, redis, 200, redisDump)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a redis rdb finding")
+		}
+		if v := dbFileExtract(res, "rdb_version"); v != "0011" {
+			t.Errorf("rdb_version=%q, want 0011", v)
+		}
+	})
+
+	t.Run("sql shown inside an html page is not a dump", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><head><title>SQL tutorial</title></head><body>" +
+			"<pre>DROP TABLE IF EXISTS users; CREATE TABLE users (id int); INSERT INTO users VALUES (1);</pre>" +
+			"</body></html>"
+		if res := runDBFileModule(t, sqlDump, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a sql file with no dump idiom is not flagged", func(t *testing.T) {
+		body := "-- migration notes\nSELECT id FROM users WHERE active = 1;\n"
+		if res := runDBFileModule(t, sqlDump, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a bare select should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a page that names the sqlite format is not the file", func(t *testing.T) {
+		body := "This page documents the SQLite format 3 on-disk structure for readers."
+		if res := runDBFileModule(t, sqlite, 200, body); len(res.Findings) > 0 {
+			t.Errorf("prose about sqlite should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a page that names redis is not an rdb snapshot", func(t *testing.T) {
+		body := "redis-server is running on this host as the REDIS cache backend."
+		if res := runDBFileModule(t, redis, 200, body); len(res.Findings) > 0 {
+			t.Errorf("prose about redis should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("the sqlite magic only counts at the start of the file", func(t *testing.T) {
+		body := "<pre>hexdump of a header: " + sqliteFile + "</pre>"
+		if res := runDBFileModule(t, sqlite, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an embedded sqlite header should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("the rdb magic only counts at the start of the file", func(t *testing.T) {
+		body := "log line: loaded snapshot " + redisDump
+		if res := runDBFileModule(t, redis, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an embedded rdb header should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{sqlDump, sqlite, redis} {
+			if res := runDBFileModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{sqlDump, sqlite, redis} {
+			if res := runDBFileModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/db_panels_test.go

@@ -0,0 +1,88 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runDBModule(t *testing.T, file string, status int, headers map[string]string, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		for k, v := range headers {
+			w.Header().Set(k, v)
+		}
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func dbExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestDBPanelModules(t *testing.T) {
+	const adminer = "../../modules/info/adminer-panel.yaml"
+	const phpmyadmin = "../../modules/info/phpmyadmin-panel.yaml"
+
+	adminerLogin := `<form action=""><input type="hidden" name="auth[driver]" value="server">` +
+		`<input name="auth[username]"></form>` +
+		`<p class="links"><a href="https://www.adminer.org/">Adminer</a> <span class="version">4.8.1</span></p>`
+	pmaLogin := `<link rel="stylesheet" href="themes/pmahomme/css/theme.css">` +
+		`<input type="text" name="pma_username"><script>var data = {"PMA_VERSION":"5.2.1"};</script>`
+
+	t.Run("adminer login", func(t *testing.T) {
+		res := runDBModule(t, adminer, 200, nil, adminerLogin)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an adminer finding")
+		}
+		if v := dbExtract(res, "adminer_version"); v != "4.8.1" {
+			t.Errorf("adminer_version=%q, want 4.8.1", v)
+		}
+	})
+
+	t.Run("adminer unrelated page", func(t *testing.T) {
+		if res := runDBModule(t, adminer, 200, nil, "<html><body>nothing</body></html>"); len(res.Findings) > 0 {
+			t.Errorf("unrelated page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("phpmyadmin login", func(t *testing.T) {
+		res := runDBModule(t, phpmyadmin, 200, map[string]string{"Set-Cookie": "phpMyAdmin=abc123; path=/"}, pmaLogin)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a phpmyadmin finding")
+		}
+		if v := dbExtract(res, "phpmyadmin_version"); v != "5.2.1" {
+			t.Errorf("phpmyadmin_version=%q, want 5.2.1", v)
+		}
+	})
+
+	t.Run("phpmyadmin unrelated page", func(t *testing.T) {
+		if res := runDBModule(t, phpmyadmin, 200, nil, "<html><body>nothing</body></html>"); len(res.Findings) > 0 {
+			t.Errorf("unrelated page should not match, got %d findings", len(res.Findings))
+		}
+	})
+}

internal/modules/debug_exposure_test.go

@@ -0,0 +1,121 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runDebugModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func debugExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestDebugExposureModules(t *testing.T) {
+	const ignition = "../../modules/recon/laravel-ignition-exposure.yaml"
+	const profiler = "../../modules/recon/symfony-profiler-exposure.yaml"
+	const heapdump = "../../modules/recon/spring-heapdump-exposure.yaml"
+
+	t.Run("ignition health check exposes command execution", func(t *testing.T) {
+		res := runDebugModule(t, ignition, 200, `{"can_execute_commands":true,"config":{}}`)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an ignition finding")
+		}
+		if v := debugExtract(res, "can_execute_commands"); v != "true" {
+			t.Errorf("can_execute_commands=%q, want true", v)
+		}
+	})
+
+	t.Run("ignition exposed with debug off still flags and extracts false", func(t *testing.T) {
+		res := runDebugModule(t, ignition, 200, `{"can_execute_commands":false}`)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an ignition finding even when command execution is off")
+		}
+		if v := debugExtract(res, "can_execute_commands"); v != "false" {
+			t.Errorf("can_execute_commands=%q, want false", v)
+		}
+	})
+
+	t.Run("symfony profiler exposes a request token", func(t *testing.T) {
+		body := `<html><head><title>Symfony Profiler</title></head><body>` +
+			`<a href="/_profiler/5f3a2b">GET /</a></body></html>`
+		res := runDebugModule(t, profiler, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a symfony profiler finding")
+		}
+		if v := debugExtract(res, "profiler_token"); v != "5f3a2b" {
+			t.Errorf("profiler_token=%q, want 5f3a2b", v)
+		}
+	})
+
+	t.Run("spring heap dump exposes the hprof magic", func(t *testing.T) {
+		body := "JAVA PROFILE 1.0.2\x00\x00\x00\x08heap bytes follow"
+		res := runDebugModule(t, heapdump, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a heap dump finding")
+		}
+		if v := debugExtract(res, "hprof_version"); v != "1.0.2" {
+			t.Errorf("hprof_version=%q, want 1.0.2", v)
+		}
+	})
+
+	t.Run("the hprof magic must be at the start not merely present", func(t *testing.T) {
+		body := "<html><body>docs about the JAVA PROFILE 1.0.2 hprof header</body></html>"
+		if res := runDebugModule(t, heapdump, 200, body); len(res.Findings) > 0 {
+			t.Errorf("the magic away from the start should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a page that only names ignition is not the endpoint", func(t *testing.T) {
+		body := `<html><body>we use ignition to render errors in development</body></html>`
+		if res := runDebugModule(t, ignition, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a prose mention should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{ignition, profiler, heapdump} {
+			if res := runDebugModule(t, file, 200, "<html><body>plain</body></html>"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{ignition, profiler, heapdump} {
+			if res := runDebugModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/deploy_config_exposure_test.go

@@ -0,0 +1,134 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runDeployModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func deployExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestDeployConfigExposureModules(t *testing.T) {
+	const vscode = "../../modules/recon/vscode-sftp-exposure.yaml"
+	const sublime = "../../modules/recon/sublime-sftp-exposure.yaml"
+	const ftpconfig = "../../modules/recon/ftpconfig-exposure.yaml"
+
+	t.Run("vscode sftp config leaks the deploy host", func(t *testing.T) {
+		body := `{"name":"prod","host":"deploy.example.com","protocol":"sftp",` +
+			`"username":"root","password":"s3cr3t","remotePath":"/var/www","uploadOnSave":true}`
+		res := runDeployModule(t, vscode, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a vscode sftp finding")
+		}
+		if v := deployExtract(res, "remote_host"); v != "deploy.example.com" {
+			t.Errorf("remote_host=%q, want deploy.example.com", v)
+		}
+	})
+
+	t.Run("vscode sftp config with key auth still flags and extracts the host", func(t *testing.T) {
+		body := `{"host":"key.example.com","protocol":"sftp",` +
+			`"username":"deploy","privateKeyPath":"~/.ssh/id_rsa","uploadOnSave":true}`
+		res := runDeployModule(t, vscode, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a vscode sftp finding for a key-auth config")
+		}
+		if v := deployExtract(res, "remote_host"); v != "key.example.com" {
+			t.Errorf("remote_host=%q, want key.example.com", v)
+		}
+	})
+
+	t.Run("sublime sftp config leaks the deploy host", func(t *testing.T) {
+		body := `{"type":"sftp","host":"sftp.example.org","user":"www","password":"hunter2",` +
+			`"remote_path":"/srv","upload_on_save":true,"sync_down_on_open":false}`
+		res := runDeployModule(t, sublime, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a sublime sftp finding")
+		}
+		if v := deployExtract(res, "remote_host"); v != "sftp.example.org" {
+			t.Errorf("remote_host=%q, want sftp.example.org", v)
+		}
+	})
+
+	t.Run("atom remote-ftp config leaks the deploy host", func(t *testing.T) {
+		body := `{"protocol":"ftp","host":"ftp.example.net","port":21,"user":"upload",` +
+			`"pass":"letmein","remote":"/","connTimeout":10000,"pasvTimeout":10000}`
+		res := runDeployModule(t, ftpconfig, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an atom remote-ftp finding")
+		}
+		if v := deployExtract(res, "remote_host"); v != "ftp.example.net" {
+			t.Errorf("remote_host=%q, want ftp.example.net", v)
+		}
+	})
+
+	t.Run("an html login page carrying the same keys is not a leak", func(t *testing.T) {
+		body := `<html><head><title>Sign in</title></head><body>` +
+			`config keys "remotePath" "password" "host":"evil.example.com"</body></html>`
+		if res := runDeployModule(t, vscode, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain json config without the tool keys is not a leak", func(t *testing.T) {
+		body := `{"host":"db.internal","username":"admin","user":"admin","pass":"x","password":"hunter2"}`
+		for _, file := range []string{vscode, sublime, ftpconfig} {
+			if res := runDeployModule(t, file, 200, body); len(res.Findings) > 0 {
+				t.Errorf("%s: a config without the tool keys should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a tool config with a host but no credential field is not a leak", func(t *testing.T) {
+		bodies := map[string]string{
+			vscode:    `{"host":"h.example.com","remotePath":"/var/www","uploadOnSave":true}`,
+			sublime:   `{"type":"sftp","host":"h.example.com","upload_on_save":true}`,
+			ftpconfig: `{"protocol":"ftp","host":"h.example.com","connTimeout":10000,"pasvTimeout":10000}`,
+		}
+		for file, body := range bodies {
+			if res := runDeployModule(t, file, 200, body); len(res.Findings) > 0 {
+				t.Errorf("%s: a config with no credential field should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{vscode, sublime, ftpconfig} {
+			if res := runDeployModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/distributed_db_exposure_test.go

@@ -0,0 +1,159 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runDistDBModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func distDBExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestDistributedDBExposureModules(t *testing.T) {
+	const riak = "../../modules/recon/riak-api-exposure.yaml"
+	const couchbase = "../../modules/recon/couchbase-api-exposure.yaml"
+	const druid = "../../modules/recon/druid-api-exposure.yaml"
+
+	riakStats := `{"riak_kv_version":"3.0.16","riak_core_version":"3.0.99","riak_pipe_version":"3.0.16",` +
+		`"sys_otp_release":"22","ring_members":["riak@10.0.0.1"],"ring_num_partitions":64,` +
+		`"storage_backend":"riak_kv_bitcask_backend"}`
+
+	couchbasePools := `{"pools":[{"name":"default","uri":"/pools/default?uuid=abc",` +
+		`"streamingUri":"/poolsStreaming/default?uuid=abc"}],"isAdminCreds":false,"isEnterprise":true,` +
+		`"implementationVersion":"7.2.0-6053-enterprise","uuid":"abc",` +
+		`"componentsVersion":{"ns_server":"7.2.0-6053","couchdb":"3.1.1"}}`
+
+	druidStatus := `{"version":"0.22.1","modules":[{"name":"org.apache.druid.server.initialization.jetty.JettyServerModule",` +
+		`"artifact":"druid-server","version":"0.22.1"},{"name":"org.apache.druid.guice.AnnouncerModule",` +
+		`"artifact":"druid-server","version":"0.22.1"}],"memory":{"maxMemory":1037959168,` +
+		`"totalMemory":1037959168,"freeMemory":900000000,"directMemory":134217728}}`
+
+	t.Run("an exposed riak http api is flagged and versioned", func(t *testing.T) {
+		res := runDistDBModule(t, riak, 200, riakStats)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a riak finding")
+		}
+		if v := distDBExtract(res, "riak_version"); v != "3.0.16" {
+			t.Errorf("riak_version=%q, want 3.0.16", v)
+		}
+	})
+
+	t.Run("an exposed couchbase cluster api is flagged and versioned", func(t *testing.T) {
+		res := runDistDBModule(t, couchbase, 200, couchbasePools)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a couchbase finding")
+		}
+		if v := distDBExtract(res, "couchbase_version"); v != "7.2.0-6053-enterprise" {
+			t.Errorf("couchbase_version=%q, want 7.2.0-6053-enterprise", v)
+		}
+	})
+
+	t.Run("an exposed druid process is flagged and versioned", func(t *testing.T) {
+		res := runDistDBModule(t, druid, 200, druidStatus)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a druid finding")
+		}
+		if v := distDBExtract(res, "druid_version"); v != "0.22.1" {
+			t.Errorf("druid_version=%q, want 0.22.1", v)
+		}
+	})
+
+	t.Run("a riak kv version without a core version is not flagged", func(t *testing.T) {
+		body := `{"riak_kv_version":"3.0.16","name":"app"}`
+		if res := runDistDBModule(t, riak, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a kv version alone should not match riak, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a riak core version without a kv version is not flagged", func(t *testing.T) {
+		body := `{"riak_core_version":"3.0.16","name":"app"}`
+		if res := runDistDBModule(t, riak, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a core version alone should not match riak, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a couchbase impl version without a components version is not flagged", func(t *testing.T) {
+		body := `{"implementationVersion":"7.2.0","name":"app"}`
+		if res := runDistDBModule(t, couchbase, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an impl version alone should not match couchbase, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a couchbase components version without an impl version is not flagged", func(t *testing.T) {
+		body := `{"componentsVersion":{"ns_server":"7.2.0"},"name":"app"}`
+		if res := runDistDBModule(t, couchbase, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a components version alone should not match couchbase, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a druid package without a memory block is not flagged", func(t *testing.T) {
+		body := `{"modules":[{"name":"org.apache.druid.cli.Main"}],"app":"x"}`
+		if res := runDistDBModule(t, druid, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a druid package alone should not match druid, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a memory block without a druid package is not flagged", func(t *testing.T) {
+		body := `{"memory":{"maxMemory":123},"app":"x"}`
+		if res := runDistDBModule(t, druid, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a memory block alone should not match druid, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic version json is not a distributed db", func(t *testing.T) {
+		body := `{"version":"1.0.0","name":"app"}`
+		for _, file := range []string{riak, couchbase, druid} {
+			if res := runDistDBModule(t, file, 200, body); len(res.Findings) > 0 {
+				t.Errorf("%s: a generic version should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{riak, couchbase, druid} {
+			if res := runDistDBModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{riak, couchbase, druid} {
+			if res := runDistDBModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/dotfile_credential_exposure_test.go

@@ -0,0 +1,164 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runDotfileModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func dotfileExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestDotfileCredentialExposureModules(t *testing.T) {
+	const netrc = "../../modules/recon/netrc-exposure.yaml"
+	const pgpass = "../../modules/recon/pgpass-exposure.yaml"
+	const mycnf = "../../modules/recon/mysql-client-config-exposure.yaml"
+
+	netrcBody := "machine api.example.com\n  login deploy\n  password s3cr3tP@ss\n" +
+		"machine ftp.example.com\n  login anon\n  password anon@site\n"
+
+	pgpassBody := "db.example.com:5432:appdb:appuser:Sup3rSecret\n*:*:*:replication:replpass\n"
+
+	mycnfBody := "[client]\nuser=root\npassword=R00tPass!\nhost=127.0.0.1\nport=3306\n"
+
+	t.Run("an exposed netrc leaks the machine host", func(t *testing.T) {
+		res := runDotfileModule(t, netrc, 200, netrcBody)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a netrc finding")
+		}
+		if v := dotfileExtract(res, "netrc_machine"); v != "api.example.com" {
+			t.Errorf("netrc_machine=%q, want api.example.com", v)
+		}
+	})
+
+	t.Run("an exposed pgpass leaks the host", func(t *testing.T) {
+		res := runDotfileModule(t, pgpass, 200, pgpassBody)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a pgpass finding")
+		}
+		if v := dotfileExtract(res, "pgpass_host"); v != "db.example.com" {
+			t.Errorf("pgpass_host=%q, want db.example.com", v)
+		}
+	})
+
+	t.Run("an exposed my.cnf leaks the client user", func(t *testing.T) {
+		res := runDotfileModule(t, mycnf, 200, mycnfBody)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a my.cnf finding")
+		}
+		if v := dotfileExtract(res, "mysql_user"); v != "root" {
+			t.Errorf("mysql_user=%q, want root", v)
+		}
+	})
+
+	t.Run("prose that names machine login and password out of order is not a netrc", func(t *testing.T) {
+		body := "this machine requires a login; store the password securely"
+		if res := runDotfileModule(t, netrc, 200, body); len(res.Findings) > 0 {
+			t.Errorf("out of order prose should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a netrc is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>machine api.example.com login deploy password s3cret</pre></body></html>"
+		if res := runDotfileModule(t, netrc, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html netrc tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a yaml db config with colon keys is not a pgpass", func(t *testing.T) {
+		body := "database:\n  host: db.example.com\n  port: 5432\n  user: appuser\n  password: secret\n"
+		if res := runDotfileModule(t, pgpass, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a yaml db config should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a pgpass shaped line with a non numeric port is not flagged", func(t *testing.T) {
+		body := "db.example.com:default:appdb:appuser:Sup3rSecret\n"
+		if res := runDotfileModule(t, pgpass, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a non numeric port should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a multi line config with a number field does not match across lines", func(t *testing.T) {
+		body := "timeout:30:seconds configured\nsee http://docs.example.com:8080 for details\n"
+		if res := runDotfileModule(t, pgpass, 200, body); len(res.Findings) > 0 {
+			t.Errorf("fields must stay on one line, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a pgpass is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html>\n<html><body><pre>\ndb.example.com:5432:appdb:appuser:secret\n</pre></body></html>\n"
+		if res := runDotfileModule(t, pgpass, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html pgpass tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a my.cnf client section without a password is not flagged", func(t *testing.T) {
+		body := "[client]\nuser=root\nhost=localhost\nport=3306\n"
+		if res := runDotfileModule(t, mycnf, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a section without a password should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a password line without a my.cnf section is not flagged", func(t *testing.T) {
+		body := "password=hunter2\nfoo=bar\n"
+		if res := runDotfileModule(t, mycnf, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a password without a section should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating a my.cnf is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>[client]\npassword=secret</pre></body></html>"
+		if res := runDotfileModule(t, mycnf, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html my.cnf tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{netrc, pgpass, mycnf} {
+			if res := runDotfileModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{netrc, pgpass, mycnf} {
+			if res := runDotfileModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/env_exposure_test.go

@@ -0,0 +1,84 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+// runEnvModule runs the env exposure module end to end against a server that
+// returns the same status and body for every path it requests.
+func runEnvModule(t *testing.T, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule("../../modules/recon/env-file-exposure.yaml")
+	if err != nil {
+		t.Fatalf("parse: %v", err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute: %v", err)
+	}
+	return res
+}
+
+func envLeakedKey(res *modules.Result) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted["leaked_key"]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestEnvFileExposureModule(t *testing.T) {
+	realEnv := "APP_NAME=Acme\nAPP_KEY=base64:Zm9vYmFy\nDB_PASSWORD=s3cr3t\nMAIL_PASSWORD=hunter2\n"
+	htmlMentionsSecret := "<!DOCTYPE html>\n<html><head><title>Docs</title></head><body>" +
+		"<code>APP_KEY=base64:...</code> put DB_PASSWORD= in your .env</body></html>"
+
+	t.Run("real env body leaks", func(t *testing.T) {
+		res := runEnvModule(t, 200, realEnv)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a finding for a real .env body")
+		}
+		if key := envLeakedKey(res); key != "APP_KEY" {
+			t.Errorf("leaked_key=%q, want APP_KEY", key)
+		}
+	})
+
+	t.Run("html page mentioning a key is not a leak", func(t *testing.T) {
+		if res := runEnvModule(t, 200, htmlMentionsSecret); len(res.Findings) > 0 {
+			t.Errorf("html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("secrets behind a 404 are not a leak", func(t *testing.T) {
+		if res := runEnvModule(t, 404, realEnv); len(res.Findings) > 0 {
+			t.Errorf("404 should not match, got %d findings", len(res.Findings))
+		}
+	})
+}

internal/modules/executor.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
@@ -13,19 +13,29 @@
 package modules
 
 import (
+	"bufio"
 	"context"
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
+	"os"
 	"regexp"
 	"strings"
 	"sync"
 	"time"
+
+	"github.com/tidwall/gjson"
 )
 
 // MaxBodySize limits response body to prevent memory exhaustion.
 const MaxBodySize = 5 * 1024 * 1024
 
+// ErrUnsupportedModuleType signals an executor for a module type that is not
+// yet implemented. Returning it (rather than an empty result) keeps callers
+// from mistaking "not implemented" for "scanned, found nothing".
+var ErrUnsupportedModuleType = errors.New("unsupported module type")
+
 // httpRequest represents a generated HTTP request.
 type httpRequest struct {
 	Method   string
@@ -63,7 +73,10 @@ func ExecuteHTTPModule(ctx context.Context, target string, def *YAMLModule, opts
 	}
 
 	// Generate requests based on paths and payloads
-	requests := generateHTTPRequests(target, cfg)
+	requests, err := generateHTTPRequests(target, cfg)
+	if err != nil {
+		return nil, err
+	}
 
 	// Determine thread count
 	threads := cfg.Threads
@@ -117,9 +130,14 @@ func ExecuteHTTPModule(ctx context.Context, target string, def *YAMLModule, opts
 }
 
 // generateHTTPRequests creates all requests based on paths and payloads.
-func generateHTTPRequests(target string, cfg *HTTPConfig) []*httpRequest {
+func generateHTTPRequests(target string, cfg *HTTPConfig) ([]*httpRequest, error) {
 	var requests []*httpRequest
 
+	paths, err := resolvePaths(cfg)
+	if err != nil {
+		return nil, err
+	}
+
 	// Ensure target has no trailing slash
 	target = strings.TrimSuffix(target, "/")
 
@@ -130,7 +148,7 @@ func generateHTTPRequests(target string, cfg *HTTPConfig) []*httpRequest {
 
 	// If no payloads, just use paths directly
 	if len(cfg.Payloads) == 0 {
-		for _, path := range cfg.Paths {
+		for _, path := range paths {
 			url := substituteVariables(path, target, "")
 			requests = append(requests, &httpRequest{
 				Method:   method,
@@ -140,26 +158,106 @@ func generateHTTPRequests(target string, cfg *HTTPConfig) []*httpRequest {
 				Original: path,
 			})
 		}
-		return requests
+		return requests, nil
 	}
 
-	// Generate requests with payloads
-	for _, path := range cfg.Paths {
+	// pitchfork pairs path[i] with payload[i] and stops at the shorter list;
+	// clusterbomb (default) crosses every path with every payload.
+	if strings.EqualFold(cfg.Attack, "pitchfork") {
+		n := len(paths)
+		if len(cfg.Payloads) < n {
+			n = len(cfg.Payloads)
+		}
+		for i := 0; i < n; i++ {
+			requests = append(requests, newPayloadRequest(method, target, paths[i], cfg.Payloads[i], cfg))
+		}
+		return requests, nil
+	}
+
+	for _, path := range paths {
 		for _, payload := range cfg.Payloads {
-			url := substituteVariables(path, target, payload)
-			body := substituteVariables(cfg.Body, target, payload)
-			requests = append(requests, &httpRequest{
-				Method:   method,
-				URL:      url,
-				Headers:  cfg.Headers,
-				Body:     body,
-				Payload:  payload,
-				Original: path,
-			})
+			requests = append(requests, newPayloadRequest(method, target, path, payload, cfg))
 		}
 	}
 
-	return requests
+	return requests, nil
+}
+
+// resolvePaths expands a wordlist over any {{word}} path templates so one
+// "{{BaseURL}}/{{word}}" path fuzzes the whole list; paths without {{word}}
+// pass through literally. no wordlist leaves cfg.Paths untouched.
+func resolvePaths(cfg *HTTPConfig) ([]string, error) {
+	if cfg.Wordlist == "" {
+		return cfg.Paths, nil
+	}
+
+	words, err := loadWordlist(cfg.Wordlist)
+	if err != nil {
+		return nil, err
+	}
+
+	var paths []string
+	for _, path := range cfg.Paths {
+		if !strings.Contains(path, "{{word}}") && !strings.Contains(path, "{{Word}}") {
+			paths = append(paths, path)
+			continue
+		}
+		for _, word := range words {
+			expanded := strings.ReplaceAll(path, "{{word}}", word)
+			expanded = strings.ReplaceAll(expanded, "{{Word}}", word)
+			paths = append(paths, expanded)
+		}
+	}
+
+	return paths, nil
+}
+
+// loadWordlist reads non-empty lines from a local wordlist file, mirroring the
+// dirlist scanner's scanLines so a converted module fuzzes the identical words.
+func loadWordlist(path string) ([]string, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, fmt.Errorf("open wordlist %q: %w", path, err)
+	}
+	defer f.Close()
+
+	var words []string
+	scanner := bufio.NewScanner(f)
+	scanner.Split(bufio.ScanLines)
+	for scanner.Scan() {
+		if line := scanner.Text(); line != "" {
+			words = append(words, line)
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		return nil, fmt.Errorf("read wordlist %q: %w", path, err)
+	}
+
+	return words, nil
+}
+
+// newPayloadRequest builds one request with the path and body templates
+// substituted for the given payload.
+func newPayloadRequest(method, target, path, payload string, cfg *HTTPConfig) *httpRequest {
+	return &httpRequest{
+		Method:   method,
+		URL:      substituteVariables(path, target, payload),
+		Headers:  cfg.Headers,
+		Body:     substituteVariables(cfg.Body, target, payload),
+		Payload:  payload,
+		Original: path,
+	}
+}
+
+// validateAttack rejects an attack mode that is not "", "clusterbomb", or
+// "pitchfork"; an empty value defaults to clusterbomb.
+func validateAttack(attack string) error {
+	switch strings.ToLower(attack) {
+	case "", "clusterbomb", "pitchfork":
+		return nil
+	default:
+		return fmt.Errorf("invalid attack %q (want \"clusterbomb\" or \"pitchfork\")", attack)
+	}
 }
 
 // substituteVariables replaces template variables in a string.
@@ -206,45 +304,63 @@ func executeHTTPRequest(ctx context.Context, client *http.Client, r *httpRequest
 	bodyStr := string(respBody)
 
 	// Check matchers
-	if !checkMatchers(cfg.Matchers, resp, bodyStr) {
+	if !checkMatchers(cfg.Matchers, cfg.MatchersCondition, resp, bodyStr) {
 		return Finding{}, false
 	}
 
 	// Extract data
 	extracted := runExtractors(cfg.Extractors, resp, bodyStr)
 
+	// favicon-only matches fire on binary icon bytes; report the hash, not the body.
+	evidence := truncateEvidence(bodyStr)
+	if fav, ok := faviconEvidence(cfg.Matchers, bodyStr); ok {
+		evidence = fav
+	}
+
 	return Finding{
 		URL:       r.URL,
 		Severity:  severity,
-		Evidence:  truncateEvidence(bodyStr),
+		Evidence:  evidence,
 		Extracted: extracted,
 	}, true
 }
 
-// checkMatchers evaluates all matchers against the response.
-func checkMatchers(matchers []Matcher, resp *http.Response, body string) bool {
+// checkMatchers combines matchers with condition "and" (default, all match) or "or" (any).
+func checkMatchers(matchers []Matcher, condition string, resp *http.Response, body string) bool {
 	if len(matchers) == 0 {
 		return false
 	}
 
-	// Default to AND condition across matchers
-	for _, m := range matchers {
-		matched := checkMatcher(m, resp, body)
-		if m.Negative {
+	or := strings.EqualFold(condition, "or")
+	for i := range matchers {
+		matched := checkMatcher(&matchers[i], resp, body)
+		if matchers[i].Negative {
 			matched = !matched
 		}
-		if !matched {
-			return false // AND logic
+		if or && matched {
+			return true
+		}
+		if !or && !matched {
+			return false
 		}
 	}
 
-	return true
+	// and: all matched; or: none matched.
+	return !or
+}
+
+// validateMatchersCondition rejects a matchers-condition that is not "", "and", or "or".
+func validateMatchersCondition(condition string) error {
+	switch strings.ToLower(condition) {
+	case "", "and", "or":
+		return nil
+	default:
+		return fmt.Errorf("invalid matchers-condition %q (want \"and\" or \"or\")", condition)
+	}
 }
 
 // checkMatcher evaluates a single matcher.
-func checkMatcher(m Matcher, resp *http.Response, body string) bool {
-	part := getPart(m.Part, resp, body)
-
+func checkMatcher(m *Matcher, resp *http.Response, body string) bool {
 	switch m.Type {
 	case "status":
 		for _, status := range m.Status {
@@ -255,10 +371,22 @@ func checkMatcher(m Matcher, resp *http.Response, body string) bool {
 		return false
 
 	case "word":
-		return checkWords(part, m.Words, m.Condition)
+		return checkWords(getPart(m.Part, resp, body), m.Words, m.Condition)
 
 	case "regex":
-		return checkRegex(part, m.Regex, m.Condition)
+		return checkRegex(getPart(m.Part, resp, body), m.Regex, m.Condition)
+
+	case "favicon":
+		return checkFaviconHash(body, m.Hash)
+
+	case "size":
+		// size matches the response body length against any listed value.
+		for _, n := range m.Size {
+			if len(body) == n {
+				return true
+			}
+		}
+		return false
 
 	default:
 		return false
@@ -350,10 +478,9 @@ func runExtractors(extractors []Extractor, resp *http.Response, body string) map
 	result := make(map[string]string)
 
 	for _, e := range extractors {
-		part := getPart(e.Part, resp, body)
-
 		switch e.Type {
 		case "regex":
+			part := getPart(e.Part, resp, body)
 			for _, pattern := range e.Regex {
 				re, err := regexp.Compile(pattern)
 				if err != nil {
@@ -365,6 +492,24 @@ func runExtractors(extractors []Extractor, resp *http.Response, body string) map
 					break
 				}
 			}
+		case "kv":
+			// kv records response header key/values, namespaced by the extractor
+			// name when set (e.g. a headers module surfacing every header).
+			for k, v := range resp.Header {
+				key := k
+				if e.Name != "" {
+					key = e.Name + "." + k
+				}
+				result[key] = strings.Join(v, ", ")
+			}
+		case "json":
+			part := getPart(e.Part, resp, body)
+			for _, path := range e.JSON {
+				if r := gjson.Get(part, path); r.Exists() {
+					result[e.Name] = r.String()
+					break
+				}
+			}
 		}
 	}
 
@@ -380,22 +525,16 @@ func truncateEvidence(s string) string {
 	return s
 }
 
-// ExecuteDNSModule runs a DNS-based module (stub for now).
-func ExecuteDNSModule(ctx context.Context, target string, def *YAMLModule, opts Options) (*Result, error) {
-	// TODO: Implement DNS module execution
-	return &Result{
-		ModuleID: def.ID,
-		Target:   target,
-		Findings: []Finding{},
-	}, nil
+// ExecuteDNSModule runs a DNS-based module (not yet implemented).
+// returns ErrUnsupportedModuleType so the caller logs a clear failure rather
+// than reporting an empty (but successful-looking) result.
+func ExecuteDNSModule(_ context.Context, _ string, def *YAMLModule, _ Options) (*Result, error) {
+	return nil, fmt.Errorf("dns module %q: %w", def.ID, ErrUnsupportedModuleType)
 }
 
-// ExecuteTCPModule runs a TCP-based module (stub for now).
-func ExecuteTCPModule(ctx context.Context, target string, def *YAMLModule, opts Options) (*Result, error) {
-	// TODO: Implement TCP module execution
-	return &Result{
-		ModuleID: def.ID,
-		Target:   target,
-		Findings: []Finding{},
-	}, nil
+// ExecuteTCPModule runs a TCP-based module (not yet implemented).
+// returns ErrUnsupportedModuleType so the caller logs a clear failure rather
+// than reporting an empty (but successful-looking) result.
+func ExecuteTCPModule(_ context.Context, _ string, def *YAMLModule, _ Options) (*Result, error) {
+	return nil, fmt.Errorf("tcp module %q: %w", def.ID, ErrUnsupportedModuleType)
 }

internal/modules/executor_test.go

@@ -0,0 +1,387 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"context"
+	"errors"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/httpx"
+)
+
+const testTimeout = 5 * time.Second
+
+// TestExecuteHTTPModuleMatchAndExtract drives the full executor against a live
+// httptest server: a request hits a path, a matcher fires, an extractor captures.
+func TestExecuteHTTPModuleMatchAndExtract(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/admin" {
+			w.Header().Set("X-App", "demo")
+			w.WriteHeader(http.StatusOK)
+			_, _ = w.Write([]byte(`flag{found-it} session=sess-4242`))
+			return
+		}
+		w.WriteHeader(http.StatusNotFound)
+	}))
+	defer srv.Close()
+
+	def := &YAMLModule{
+		ID:   "test-http-hit",
+		Type: TypeHTTP,
+		Info: YAMLModuleInfo{Severity: "high"},
+		HTTP: &HTTPConfig{
+			Method: "GET",
+			Paths:  []string{"{{BaseURL}}/admin", "{{BaseURL}}/missing"},
+			Matchers: []Matcher{
+				{Type: "status", Status: []int{200}},
+				{Type: "word", Part: "body", Words: []string{"flag{found-it}"}},
+			},
+			Extractors: []Extractor{
+				{Type: "regex", Name: "session", Part: "body", Regex: []string{`session=(\S+)`}, Group: 1},
+			},
+		},
+	}
+
+	// route through the shared httpx client so proxy/-H/-rate-limit would apply.
+	opts := Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)}
+
+	result, err := ExecuteHTTPModule(context.Background(), srv.URL, def, opts)
+	if err != nil {
+		t.Fatalf("ExecuteHTTPModule: %v", err)
+	}
+
+	// only /admin satisfies status+word, /missing returns 404.
+	if len(result.Findings) != 1 {
+		t.Fatalf("got %d findings, want 1", len(result.Findings))
+	}
+	f := result.Findings[0]
+	if f.Severity != "high" {
+		t.Errorf("severity = %q, want high (carried from Info)", f.Severity)
+	}
+	if f.Extracted["session"] != "sess-4242" {
+		t.Errorf("extracted session = %q, want sess-4242", f.Extracted["session"])
+	}
+	if f.URL != srv.URL+"/admin" {
+		t.Errorf("finding url = %q, want %q", f.URL, srv.URL+"/admin")
+	}
+}
+
+// TestExecuteHTTPModuleNoMatch confirms a module that matches nothing reports
+// zero findings without erroring.
+func TestExecuteHTTPModuleNoMatch(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.WriteHeader(http.StatusOK)
+		_, _ = w.Write([]byte("nothing interesting"))
+	}))
+	defer srv.Close()
+
+	def := &YAMLModule{
+		ID:   "test-http-miss",
+		Type: TypeHTTP,
+		HTTP: &HTTPConfig{
+			Paths: []string{"{{BaseURL}}/"},
+			Matchers: []Matcher{
+				{Type: "word", Part: "body", Words: []string{"never-present"}},
+			},
+		},
+	}
+
+	result, err := ExecuteHTTPModule(context.Background(), srv.URL, def, Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)})
+	if err != nil {
+		t.Fatalf("ExecuteHTTPModule: %v", err)
+	}
+	if len(result.Findings) != 0 {
+		t.Fatalf("got %d findings, want 0", len(result.Findings))
+	}
+}
+
+// TestExecuteHTTPModulePayloadExpansion verifies payload templates reach the
+// server and the matching response is captured.
+func TestExecuteHTTPModulePayloadExpansion(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		// only the "boom" payload triggers the vulnerable branch.
+		if r.URL.Query().Get("q") == "boom" {
+			_, _ = w.Write([]byte("error: sql syntax near boom"))
+			return
+		}
+		_, _ = w.Write([]byte("ok"))
+	}))
+	defer srv.Close()
+
+	def := &YAMLModule{
+		ID:   "test-http-payload",
+		Type: TypeHTTP,
+		HTTP: &HTTPConfig{
+			Paths:    []string{"{{BaseURL}}/search?q={{payload}}"},
+			Payloads: []string{"safe", "boom"},
+			Matchers: []Matcher{
+				{Type: "word", Part: "body", Words: []string{"sql syntax"}},
+			},
+		},
+	}
+
+	result, err := ExecuteHTTPModule(context.Background(), srv.URL, def, Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)})
+	if err != nil {
+		t.Fatalf("ExecuteHTTPModule: %v", err)
+	}
+	if len(result.Findings) != 1 {
+		t.Fatalf("got %d findings, want 1 (only boom payload)", len(result.Findings))
+	}
+}
+
+// TestExecuteHTTPModuleSizeMatcher pins the size matcher: it fires when the
+// response body length equals a listed value and stays silent otherwise.
+func TestExecuteHTTPModuleSizeMatcher(t *testing.T) {
+	body := "1234567890" // 10 bytes
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	opts := Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)}
+	mod := func(id string, size int) *YAMLModule {
+		return &YAMLModule{
+			ID: id, Type: TypeHTTP,
+			HTTP: &HTTPConfig{
+				Paths:    []string{"{{BaseURL}}/"},
+				Matchers: []Matcher{{Type: "size", Size: []int{size}}},
+			},
+		}
+	}
+
+	hit, err := ExecuteHTTPModule(context.Background(), srv.URL, mod("size-hit", len(body)), opts)
+	if err != nil {
+		t.Fatalf("ExecuteHTTPModule(hit): %v", err)
+	}
+	if len(hit.Findings) != 1 {
+		t.Fatalf("size match: got %d findings, want 1", len(hit.Findings))
+	}
+
+	miss, err := ExecuteHTTPModule(context.Background(), srv.URL, mod("size-miss", len(body)+1), opts)
+	if err != nil {
+		t.Fatalf("ExecuteHTTPModule(miss): %v", err)
+	}
+	if len(miss.Findings) != 0 {
+		t.Fatalf("size mismatch: got %d findings, want 0", len(miss.Findings))
+	}
+}
+
+// TestExecuteHTTPModuleKvExtractor pins the kv extractor: it records response
+// header key/values onto the finding, namespaced by the extractor name.
+func TestExecuteHTTPModuleKvExtractor(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.Header().Set("Server", "nginx/1.25.3")
+		w.Header().Set("X-Powered-By", "PHP/8.2.0")
+		w.WriteHeader(http.StatusOK)
+		_, _ = w.Write([]byte("hello"))
+	}))
+	defer srv.Close()
+
+	def := &YAMLModule{
+		ID: "kv-mod", Type: TypeHTTP,
+		HTTP: &HTTPConfig{
+			Paths:      []string{"{{BaseURL}}/"},
+			Matchers:   []Matcher{{Type: "status", Status: []int{200}}},
+			Extractors: []Extractor{{Type: "kv", Name: "headers", Part: "header"}},
+		},
+	}
+
+	result, err := ExecuteHTTPModule(context.Background(), srv.URL, def, Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)})
+	if err != nil {
+		t.Fatalf("ExecuteHTTPModule: %v", err)
+	}
+	if len(result.Findings) != 1 {
+		t.Fatalf("got %d findings, want 1", len(result.Findings))
+	}
+	ex := result.Findings[0].Extracted
+	if ex["headers.Server"] != "nginx/1.25.3" {
+		t.Errorf("kv headers.Server = %q, want nginx/1.25.3", ex["headers.Server"])
+	}
+	if ex["headers.X-Powered-By"] != "PHP/8.2.0" {
+		t.Errorf("kv headers.X-Powered-By = %q, want PHP/8.2.0", ex["headers.X-Powered-By"])
+	}
+}
+
+func TestExecuteHTTPModuleNoConfig(t *testing.T) {
+	def := &YAMLModule{ID: "x", Type: TypeHTTP}
+	if _, err := ExecuteHTTPModule(context.Background(), "http://h", def, Options{}); err == nil {
+		t.Fatal("expected error when HTTP config is nil")
+	}
+}
+
+// TestExecuteHTTPModuleContextCancel pins the cancellation path. The dispatch
+// loop selects between ctx.Done() and the concurrency semaphore, so a cancelled
+// context can either short-circuit with ctx.Err() or let the in-flight request
+// fail on the dead context. Both are correct: the contract is "never hang, never
+// invent a finding", which is what we assert here rather than forcing one race
+// winner (that made this test flaky under -count).
+func TestExecuteHTTPModuleContextCancel(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer srv.Close()
+
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	def := &YAMLModule{
+		ID:   "test-http-cancel",
+		Type: TypeHTTP,
+		HTTP: &HTTPConfig{
+			Paths:    []string{"{{BaseURL}}/a"},
+			Matchers: []Matcher{{Type: "status", Status: []int{200}}},
+		},
+	}
+
+	result, err := ExecuteHTTPModule(ctx, srv.URL, def, Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)})
+	if err != nil {
+		if !errors.Is(err, context.Canceled) {
+			t.Fatalf("err = %v, want context.Canceled or nil", err)
+		}
+		return
+	}
+	// no error means the request was dispatched but failed on the dead context;
+	// either way a cancelled scan must not surface findings.
+	if len(result.Findings) != 0 {
+		t.Fatalf("cancelled scan produced %d findings, want 0", len(result.Findings))
+	}
+}
+
+// TestExecuteDNSModuleUnsupported pins the current behavior: DNS execution is
+// not implemented and must signal it via ErrUnsupportedModuleType, not by
+// quietly returning an empty (successful-looking) result.
+func TestExecuteDNSModuleUnsupported(t *testing.T) {
+	def := &YAMLModule{ID: "dns-mod", Type: TypeDNS, DNS: &DNSConfig{Type: "A"}}
+	result, err := ExecuteDNSModule(context.Background(), "example.com", def, Options{})
+	if result != nil {
+		t.Errorf("result = %v, want nil for unsupported type", result)
+	}
+	if !errors.Is(err, ErrUnsupportedModuleType) {
+		t.Fatalf("err = %v, want ErrUnsupportedModuleType", err)
+	}
+}
+
+func TestExecuteTCPModuleUnsupported(t *testing.T) {
+	def := &YAMLModule{ID: "tcp-mod", Type: TypeTCP, TCP: &TCPConfig{Port: 22}}
+	result, err := ExecuteTCPModule(context.Background(), "example.com", def, Options{})
+	if result != nil {
+		t.Errorf("result = %v, want nil for unsupported type", result)
+	}
+	if !errors.Is(err, ErrUnsupportedModuleType) {
+		t.Fatalf("err = %v, want ErrUnsupportedModuleType", err)
+	}
+}
+
+// TestWrapperExecuteRoutesByType confirms the Module wrapper dispatches each
+// type to the right executor and propagates the unsupported-type sentinel.
+func TestWrapperExecuteRoutesByType(t *testing.T) {
+	t.Run("dns routes to unsupported", func(t *testing.T) {
+		def := &YAMLModule{ID: "d", Type: TypeDNS, DNS: &DNSConfig{}}
+		w := newYAMLModuleWrapper(def, "d.yaml")
+		if _, err := w.Execute(context.Background(), "t", Options{}); !errors.Is(err, ErrUnsupportedModuleType) {
+			t.Fatalf("err = %v, want ErrUnsupportedModuleType", err)
+		}
+	})
+
+	t.Run("tcp routes to unsupported", func(t *testing.T) {
+		def := &YAMLModule{ID: "t", Type: TypeTCP, TCP: &TCPConfig{}}
+		w := newYAMLModuleWrapper(def, "t.yaml")
+		if _, err := w.Execute(context.Background(), "t", Options{}); !errors.Is(err, ErrUnsupportedModuleType) {
+			t.Fatalf("err = %v, want ErrUnsupportedModuleType", err)
+		}
+	})
+
+	t.Run("missing http config errors", func(t *testing.T) {
+		def := &YAMLModule{ID: "h", Type: TypeHTTP}
+		w := newYAMLModuleWrapper(def, "h.yaml")
+		if _, err := w.Execute(context.Background(), "t", Options{}); err == nil {
+			t.Fatal("expected error for missing http config")
+		}
+	})
+
+	t.Run("unknown type errors", func(t *testing.T) {
+		def := &YAMLModule{ID: "z", Type: ModuleType("bogus")}
+		w := newYAMLModuleWrapper(def, "z.yaml")
+		if _, err := w.Execute(context.Background(), "t", Options{}); err == nil {
+			t.Fatal("expected error for unknown module type")
+		}
+	})
+}
+
+// TestExecuteHTTPModuleWordlist proves a {{word}} path templated against a local
+// wordlist drives one real request per word, and only the path that exists fires.
+func TestExecuteHTTPModuleWordlist(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/admin" {
+			w.WriteHeader(http.StatusOK)
+			return
+		}
+		w.WriteHeader(http.StatusNotFound)
+	}))
+	defer srv.Close()
+
+	list := filepath.Join(t.TempDir(), "words.txt")
+	if err := os.WriteFile(list, []byte("login\nadmin\nbackup\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+
+	def := &YAMLModule{
+		ID:   "test-wordlist",
+		Type: TypeHTTP,
+		Info: YAMLModuleInfo{Severity: "low"},
+		HTTP: &HTTPConfig{
+			Method:   "GET",
+			Wordlist: list,
+			Paths:    []string{"{{BaseURL}}/{{word}}"},
+			Matchers: []Matcher{{Type: "status", Status: []int{200}}},
+		},
+	}
+
+	opts := Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)}
+	res, err := ExecuteHTTPModule(context.Background(), srv.URL, def, opts)
+	if err != nil {
+		t.Fatalf("execute: %v", err)
+	}
+	if len(res.Findings) != 1 {
+		t.Fatalf("got %d findings, want 1 (only /admin exists)", len(res.Findings))
+	}
+	if got := res.Findings[0].URL; got != srv.URL+"/admin" {
+		t.Errorf("finding url = %q, want %q", got, srv.URL+"/admin")
+	}
+}
+
+func TestTruncateEvidence(t *testing.T) {
+	short := "short evidence"
+	if got := truncateEvidence(short); got != short {
+		t.Errorf("short evidence changed: %q", got)
+	}
+
+	long := make([]byte, 600)
+	for i := range long {
+		long[i] = 'a'
+	}
+	got := truncateEvidence(string(long))
+	// 500 chars of content plus the ellipsis marker.
+	if len(got) != 503 {
+		t.Errorf("truncated len = %d, want 503", len(got))
+	}
+	if got[len(got)-3:] != "..." {
+		t.Errorf("truncated evidence missing ellipsis: %q", got[len(got)-3:])
+	}
+}

internal/modules/favicon.go

@@ -0,0 +1,82 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"fmt"
+	"math"
+
+	"github.com/dropalldatabases/sif/internal/fingerprint"
+)
+
+// checkFaviconHash reports whether the body's shodan mmh3 hash matches any
+// configured value. only the body (the icon) is hashed; part is ignored.
+func checkFaviconHash(body string, want []int64) bool {
+	if len(want) == 0 {
+		return false
+	}
+	got := fingerprint.FaviconHash([]byte(body))
+	for _, w := range want {
+		if n, ok := normalizeFaviconHash(w); ok && n == got {
+			return true
+		}
+	}
+	return false
+}
+
+// normalizeFaviconHash folds a hash to the signed int32 shodan stores, accepting
+// either 32-bit form so a signed or unsigned value pastes in as-is. out-of-range
+// values are rejected so a stray number can't wrap into a false match.
+func normalizeFaviconHash(v int64) (int32, bool) {
+	if v < math.MinInt32 || v > math.MaxUint32 {
+		return 0, false
+	}
+	return int32(uint32(v)), true //nolint:gosec // intentional 32-bit fold to shodan's signed form
+}
+
+// faviconEvidence gives the hash as evidence for a favicon-only finding, and
+// nothing when a word/regex matcher is present so its body evidence stands.
+func faviconEvidence(matchers []Matcher, body string) (string, bool) {
+	favicon := false
+	for i := range matchers {
+		switch matchers[i].Type {
+		case "word", "regex":
+			return "", false
+		case "favicon":
+			favicon = true
+		}
+	}
+	if !favicon {
+		return "", false
+	}
+	return fmt.Sprintf("favicon mmh3=%d", fingerprint.FaviconHash([]byte(body))), true
+}
+
+// validateMatchers fails favicon matchers that would silently never fire (no
+// hash, or one out of 32-bit range) at load rather than at match time.
+func validateMatchers(matchers []Matcher) error {
+	for i := range matchers {
+		if matchers[i].Type != "favicon" {
+			continue
+		}
+		if len(matchers[i].Hash) == 0 {
+			return fmt.Errorf("favicon matcher requires at least one hash")
+		}
+		for _, h := range matchers[i].Hash {
+			if _, ok := normalizeFaviconHash(h); !ok {
+				return fmt.Errorf("favicon hash %d out of range (use a signed int32 or unsigned uint32 value)", h)
+			}
+		}
+	}
+	return nil
+}

internal/modules/favicon_test.go

@@ -0,0 +1,191 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"context"
+	"fmt"
+	"math"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"github.com/dropalldatabases/sif/internal/fingerprint"
+	"github.com/dropalldatabases/sif/internal/httpx"
+)
+
+// faviconFixture hashes to a negative int32, so its signed and unsigned forms
+// differ and the unsigned-match case below actually exercises the fold.
+var faviconFixture = []byte(strings.Repeat("sif-favicon-golden-test-bytes-", 8))
+
+func TestCheckMatcherFavicon(t *testing.T) {
+	body := string(faviconFixture)
+	signed := int64(fingerprint.FaviconHash(faviconFixture))
+	if signed >= 0 {
+		t.Fatalf("fixture must hash to a negative int32 for the unsigned case to be meaningful, got %d", signed)
+	}
+	unsigned := int64(uint32(fingerprint.FaviconHash(faviconFixture)))
+
+	tests := []struct {
+		name   string
+		hashes []int64
+		expect bool
+	}{
+		{name: "signed match", hashes: []int64{signed}, expect: true},
+		{name: "unsigned match", hashes: []int64{unsigned}, expect: true},
+		{name: "one of many", hashes: []int64{1, 2, signed}, expect: true},
+		{name: "no match", hashes: []int64{1, 2, 3}, expect: false},
+		{name: "empty list", hashes: nil, expect: false},
+		{name: "out-of-range ignored", hashes: []int64{1 << 40}, expect: false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			m := &Matcher{Type: "favicon", Hash: tt.hashes}
+			resp := fakeResponse(t, 200, nil)
+			if got := checkMatcher(m, resp, body); got != tt.expect {
+				t.Errorf("checkMatcher favicon = %v, want %v", got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestNormalizeFaviconHash(t *testing.T) {
+	tests := []struct {
+		name   string
+		in     int64
+		want   int32
+		wantOK bool
+	}{
+		{name: "signed passthrough", in: -235701012, want: -235701012, wantOK: true},
+		{name: "unsigned folds to signed", in: 4059266284, want: -235701012, wantOK: true},
+		{name: "positive in range", in: 116323821, want: 116323821, wantOK: true},
+		{name: "min int32", in: math.MinInt32, want: math.MinInt32, wantOK: true},
+		{name: "max uint32 folds to -1", in: math.MaxUint32, want: -1, wantOK: true},
+		{name: "above uint32 rejected", in: math.MaxUint32 + 1, wantOK: false},
+		{name: "below int32 rejected", in: math.MinInt32 - 1, wantOK: false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, ok := normalizeFaviconHash(tt.in)
+			if ok != tt.wantOK {
+				t.Fatalf("ok = %v, want %v", ok, tt.wantOK)
+			}
+			if ok && got != tt.want {
+				t.Errorf("normalizeFaviconHash(%d) = %d, want %d", tt.in, got, tt.want)
+			}
+		})
+	}
+}
+
+func TestFaviconEvidence(t *testing.T) {
+	body := string(faviconFixture)
+	hashLine := fmt.Sprintf("favicon mmh3=%d", fingerprint.FaviconHash(faviconFixture))
+	tests := []struct {
+		name     string
+		matchers []Matcher
+		want     string
+		wantOK   bool
+	}{
+		{name: "favicon only", matchers: []Matcher{{Type: "favicon"}}, want: hashLine, wantOK: true},
+		{name: "favicon with status", matchers: []Matcher{{Type: "status"}, {Type: "favicon"}}, want: hashLine, wantOK: true},
+		{name: "favicon with word keeps body", matchers: []Matcher{{Type: "word"}, {Type: "favicon"}}, wantOK: false},
+		{name: "favicon with regex keeps body", matchers: []Matcher{{Type: "regex"}, {Type: "favicon"}}, wantOK: false},
+		{name: "no favicon matcher", matchers: []Matcher{{Type: "status"}}, wantOK: false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, ok := faviconEvidence(tt.matchers, body)
+			if ok != tt.wantOK {
+				t.Fatalf("ok = %v, want %v", ok, tt.wantOK)
+			}
+			if ok && got != tt.want {
+				t.Errorf("evidence = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestValidateMatchers(t *testing.T) {
+	tests := []struct {
+		name     string
+		matchers []Matcher
+		wantErr  bool
+	}{
+		{name: "valid signed", matchers: []Matcher{{Type: "favicon", Hash: []int64{-235701012}}}, wantErr: false},
+		{name: "valid unsigned", matchers: []Matcher{{Type: "favicon", Hash: []int64{4059266284}}}, wantErr: false},
+		{name: "favicon with no hash", matchers: []Matcher{{Type: "favicon"}}, wantErr: true},
+		{name: "out-of-range hash", matchers: []Matcher{{Type: "favicon", Hash: []int64{99999999999}}}, wantErr: true},
+		{name: "non-favicon ignored", matchers: []Matcher{{Type: "word", Words: []string{"x"}}}, wantErr: false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if err := validateMatchers(tt.matchers); (err != nil) != tt.wantErr {
+				t.Errorf("validateMatchers err = %v, wantErr %v", err, tt.wantErr)
+			}
+		})
+	}
+}
+
+// favicon composes with the negative flag like any other matcher.
+func TestCheckMatcherFaviconNegative(t *testing.T) {
+	signed := int64(fingerprint.FaviconHash(faviconFixture))
+	matchers := []Matcher{{Type: "favicon", Hash: []int64{signed}, Negative: true}}
+	resp := fakeResponse(t, 200, nil)
+	if checkMatchers(matchers, "", resp, string(faviconFixture)) {
+		t.Error("negative favicon matcher should not match its own hash")
+	}
+}
+
+// drives the full executor: fetch favicon, match on its hash, report the hash.
+func TestExecuteHTTPModuleFavicon(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/favicon.ico" {
+			w.Header().Set("Content-Type", "image/x-icon")
+			_, _ = w.Write(faviconFixture)
+			return
+		}
+		w.WriteHeader(http.StatusNotFound)
+	}))
+	defer srv.Close()
+
+	// unsigned form must still match end to end
+	unsigned := int64(uint32(fingerprint.FaviconHash(faviconFixture)))
+	def := &YAMLModule{
+		ID:   "favicon-fp",
+		Type: TypeHTTP,
+		Info: YAMLModuleInfo{Severity: "info"},
+		HTTP: &HTTPConfig{
+			Method: "GET",
+			Paths:  []string{"{{BaseURL}}/favicon.ico"},
+			Matchers: []Matcher{
+				{Type: "status", Status: []int{200}},
+				{Type: "favicon", Hash: []int64{unsigned}},
+			},
+		},
+	}
+
+	opts := Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)}
+	result, err := ExecuteHTTPModule(context.Background(), srv.URL, def, opts)
+	if err != nil {
+		t.Fatalf("ExecuteHTTPModule: %v", err)
+	}
+	if len(result.Findings) != 1 {
+		t.Fatalf("got %d findings, want 1", len(result.Findings))
+	}
+
+	wantEvidence := fmt.Sprintf("favicon mmh3=%d", fingerprint.FaviconHash(faviconFixture))
+	if got := result.Findings[0].Evidence; got != wantEvidence {
+		t.Errorf("evidence = %q, want %q", got, wantEvidence)
+	}
+}

internal/modules/http_database_exposure_test.go

@@ -0,0 +1,168 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runHTTPDBModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func httpdbExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestHTTPDatabaseExposureModules(t *testing.T) {
+	const influxdb = "../../modules/recon/influxdb-api-exposure.yaml"
+	const arangodb = "../../modules/recon/arangodb-api-exposure.yaml"
+	const neo4j = "../../modules/recon/neo4j-api-exposure.yaml"
+
+	influxHealth := `{"name":"influxdb","message":"ready for queries and writes","status":"pass",` +
+		`"checks":[],"version":"2.9.1","commit":"a1b2c3d4"}`
+
+	arangoVersion := `{"server":"arango","version":"3.11.5","license":"community"}`
+
+	neo4jDiscovery := `{"bolt_routing":"neo4j://localhost:7687","transaction":"http://localhost:7474/db/{databaseName}/tx",` +
+		`"bolt_direct":"bolt://localhost:7687","neo4j_version":"5.13.0","neo4j_edition":"community"}`
+
+	t.Run("an exposed influxdb health endpoint is flagged and versioned", func(t *testing.T) {
+		res := runHTTPDBModule(t, influxdb, 200, influxHealth)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an influxdb finding")
+		}
+		if v := httpdbExtract(res, "influxdb_version"); v != "2.9.1" {
+			t.Errorf("influxdb_version=%q, want 2.9.1", v)
+		}
+	})
+
+	t.Run("an anonymous arangodb version endpoint is flagged and versioned", func(t *testing.T) {
+		res := runHTTPDBModule(t, arangodb, 200, arangoVersion)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an arangodb finding")
+		}
+		if v := httpdbExtract(res, "arangodb_version"); v != "3.11.5" {
+			t.Errorf("arangodb_version=%q, want 3.11.5", v)
+		}
+	})
+
+	t.Run("an exposed neo4j discovery endpoint is flagged and versioned", func(t *testing.T) {
+		res := runHTTPDBModule(t, neo4j, 200, neo4jDiscovery)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a neo4j finding")
+		}
+		if v := httpdbExtract(res, "neo4j_version"); v != "5.13.0" {
+			t.Errorf("neo4j_version=%q, want 5.13.0", v)
+		}
+	})
+
+	t.Run("an influxdb name without the health message is not flagged", func(t *testing.T) {
+		body := `{"name":"influxdb","status":"pass"}`
+		if res := runHTTPDBModule(t, influxdb, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an influxdb name alone should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a health message without the influxdb name is not flagged", func(t *testing.T) {
+		body := `{"name":"telegraf","message":"ready for queries and writes"}`
+		if res := runHTTPDBModule(t, influxdb, 200, body); len(res.Findings) > 0 {
+			t.Errorf("the message alone should not match influxdb, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an arango without a license field is still flagged", func(t *testing.T) {
+		body := `{"server":"arango","version":"3.11.5"}`
+		res := runHTTPDBModule(t, arangodb, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an arangodb finding without a license field (pre-3.12)")
+		}
+		if v := httpdbExtract(res, "arangodb_version"); v != "3.11.5" {
+			t.Errorf("arangodb_version=%q, want 3.11.5", v)
+		}
+	})
+
+	t.Run("a non-arango version response is not flagged", func(t *testing.T) {
+		body := `{"server":"foundationdb","version":"1.0.0"}`
+		if res := runHTTPDBModule(t, arangodb, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a non-arango server should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an arango response without a version is not flagged", func(t *testing.T) {
+		body := `{"server":"arango"}`
+		if res := runHTTPDBModule(t, arangodb, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an arango without a version should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an arango that requires auth is not flagged", func(t *testing.T) {
+		if res := runHTTPDBModule(t, arangodb, 401, arangoVersion); len(res.Findings) > 0 {
+			t.Errorf("a 401 arango should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a neo4j version without an edition is not flagged", func(t *testing.T) {
+		body := `{"neo4j_version":"5.13.0","transaction":"http://localhost:7474/db/neo4j/tx"}`
+		if res := runHTTPDBModule(t, neo4j, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a neo4j version alone should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a neo4j edition without a version is not flagged", func(t *testing.T) {
+		body := `{"neo4j_edition":"community","bolt_routing":"neo4j://localhost:7687"}`
+		if res := runHTTPDBModule(t, neo4j, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a neo4j edition alone should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic health json is not influxdb", func(t *testing.T) {
+		body := `{"status":"UP","components":{"db":{"status":"UP"}}}`
+		if res := runHTTPDBModule(t, influxdb, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic health should not match influxdb, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{influxdb, arangodb, neo4j} {
+			if res := runHTTPDBModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{influxdb, arangodb, neo4j} {
+			if res := runHTTPDBModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/infra_config_exposure_test.go

@@ -0,0 +1,151 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runInfraModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func infraExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestInfraConfigExposureModules(t *testing.T) {
+	const terraform = "../../modules/recon/terraform-state-exposure.yaml"
+	const kubeconfig = "../../modules/recon/kubeconfig-exposure.yaml"
+	const compose = "../../modules/recon/docker-compose-exposure.yaml"
+
+	t.Run("terraform state leaks the terraform version", func(t *testing.T) {
+		body := `{"version":4,"terraform_version":"1.5.7","serial":12,"lineage":"a1b2",` +
+			`"outputs":{},"resources":[{"type":"aws_db_instance","name":"main"}]}`
+		res := runInfraModule(t, terraform, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a terraform state finding")
+		}
+		if v := infraExtract(res, "terraform_version"); v != "1.5.7" {
+			t.Errorf("terraform_version=%q, want 1.5.7", v)
+		}
+	})
+
+	t.Run("terraform state with a pre-release version still extracts the number", func(t *testing.T) {
+		body := `{"version":4,"terraform_version":"0.12.0-beta1","serial":1,"lineage":"x","resources":[]}`
+		res := runInfraModule(t, terraform, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a terraform state finding")
+		}
+		if v := infraExtract(res, "terraform_version"); v != "0.12.0" {
+			t.Errorf("terraform_version=%q, want 0.12.0", v)
+		}
+	})
+
+	t.Run("kubeconfig leaks the cluster server", func(t *testing.T) {
+		body := "apiVersion: v1\nkind: Config\nclusters:\n- cluster:\n" +
+			"    server: https://10.0.0.1:6443\n  name: prod\ncurrent-context: prod\n"
+		res := runInfraModule(t, kubeconfig, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a kubeconfig finding")
+		}
+		if v := infraExtract(res, "cluster_server"); v != "https://10.0.0.1:6443" {
+			t.Errorf("cluster_server=%q, want https://10.0.0.1:6443", v)
+		}
+	})
+
+	t.Run("docker compose leaks the image version", func(t *testing.T) {
+		body := "version: \"3.8\"\nservices:\n  web:\n    image: nginx:1.25\n    ports:\n" +
+			"      - \"80:80\"\n  db:\n    image: postgres:15\n"
+		res := runInfraModule(t, compose, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a docker compose finding")
+		}
+		if v := infraExtract(res, "compose_image"); v != "nginx:1.25" {
+			t.Errorf("compose_image=%q, want nginx:1.25", v)
+		}
+	})
+
+	t.Run("a terraform_version mention without the state structure is not a leak", func(t *testing.T) {
+		body := `{"terraform_version":"1.5.7"}`
+		if res := runInfraModule(t, terraform, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a bare version mention should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a kind Config mention without the kubeconfig structure is not a leak", func(t *testing.T) {
+		body := "kind: Config\ndescription: an unrelated document\n"
+		if res := runInfraModule(t, kubeconfig, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a bare kind mention should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a services key without a service definition is not a leak", func(t *testing.T) {
+		body := "services: enabled\nnote: not a compose file\n"
+		if res := runInfraModule(t, compose, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a bare services key should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page carrying the markers is not a leak", func(t *testing.T) {
+		body := `<html><head><title>x</title></head><body>"terraform_version":"1.5.7" "lineage":"a1b2"</body></html>`
+		if res := runInfraModule(t, terraform, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{terraform, kubeconfig, compose} {
+			if res := runInfraModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{terraform, kubeconfig, compose} {
+			if res := runInfraModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/json_extractor_test.go

@@ -0,0 +1,86 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/dropalldatabases/sif/internal/httpx"
+)
+
+func TestRunExtractorsJSON(t *testing.T) {
+	const body = `{"version":"1.2.3","app":{"name":"sif"},"items":[{"id":7}]}`
+	resp := fakeResponse(t, 200, nil)
+
+	tests := []struct {
+		name  string
+		paths []string
+		want  string // "" means the extractor should set nothing
+	}{
+		{"top level", []string{"version"}, "1.2.3"},
+		{"nested", []string{"app.name"}, "sif"},
+		{"array index", []string{"items.0.id"}, "7"},
+		{"first existing wins", []string{"missing", "version"}, "1.2.3"},
+		{"no match", []string{"nope"}, ""},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			ex := []Extractor{{Type: "json", Name: "v", Part: "body", JSON: tt.paths}}
+			got := runExtractors(ex, resp, body)
+			if tt.want == "" {
+				if v, ok := got["v"]; ok {
+					t.Errorf("expected no extraction, got %q", v)
+				}
+				return
+			}
+			if got["v"] != tt.want {
+				t.Errorf("got %q, want %q", got["v"], tt.want)
+			}
+		})
+	}
+}
+
+func TestExecuteHTTPModuleJSONExtractor(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"version":"9.9.9"}`))
+	}))
+	defer srv.Close()
+
+	def := &YAMLModule{
+		ID:   "j",
+		Type: TypeHTTP,
+		Info: YAMLModuleInfo{Severity: "info"},
+		HTTP: &HTTPConfig{
+			Method:     "GET",
+			Paths:      []string{"{{BaseURL}}/"},
+			Matchers:   []Matcher{{Type: "status", Status: []int{200}}},
+			Extractors: []Extractor{{Type: "json", Name: "version", Part: "body", JSON: []string{"version"}}},
+		},
+	}
+
+	opts := Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)}
+	res, err := ExecuteHTTPModule(context.Background(), srv.URL, def, opts)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(res.Findings) != 1 {
+		t.Fatalf("got %d findings, want 1", len(res.Findings))
+	}
+	if got := res.Findings[0].Extracted["version"]; got != "9.9.9" {
+		t.Errorf("extracted version = %q, want 9.9.9", got)
+	}
+}

internal/modules/loader.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·

internal/modules/loader_test.go

@@ -0,0 +1,269 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+// writeModule drops a yaml file into a temp dir and returns its path.
+func writeModule(t *testing.T, dir, name, content string) string {
+	t.Helper()
+	path := filepath.Join(dir, name)
+	if err := os.WriteFile(path, []byte(content), 0o600); err != nil {
+		t.Fatalf("write module: %v", err)
+	}
+	return path
+}
+
+func TestParseYAMLModuleValid(t *testing.T) {
+	const doc = `id: example-http
+type: http
+info:
+  name: Example
+  author: azzie
+  severity: medium
+  description: a test module
+  tags: [test, demo]
+http:
+  method: GET
+  paths:
+    - "{{BaseURL}}/admin"
+  matchers:
+    - type: status
+      status: [200]
+    - type: word
+      part: body
+      words: ["admin"]
+      condition: and
+  extractors:
+    - type: regex
+      name: token
+      part: body
+      regex: ["token=(\\w+)"]
+      group: 1
+`
+	dir := t.TempDir()
+	path := writeModule(t, dir, "ok.yaml", doc)
+
+	def, err := ParseYAMLModule(path)
+	if err != nil {
+		t.Fatalf("ParseYAMLModule: %v", err)
+	}
+	if def.ID != "example-http" {
+		t.Errorf("id = %q, want example-http", def.ID)
+	}
+	if def.Type != TypeHTTP {
+		t.Errorf("type = %q, want http", def.Type)
+	}
+	if def.Info.Severity != "medium" {
+		t.Errorf("severity = %q, want medium", def.Info.Severity)
+	}
+	if def.HTTP == nil {
+		t.Fatal("http config not parsed")
+	}
+	if len(def.HTTP.Matchers) != 2 {
+		t.Errorf("got %d matchers, want 2", len(def.HTTP.Matchers))
+	}
+	if len(def.HTTP.Extractors) != 1 || def.HTTP.Extractors[0].Group != 1 {
+		t.Errorf("extractor not parsed correctly: %+v", def.HTTP.Extractors)
+	}
+	if len(def.Info.Tags) != 2 {
+		t.Errorf("got %d tags, want 2", len(def.Info.Tags))
+	}
+}
+
+func TestParseYAMLModuleErrors(t *testing.T) {
+	dir := t.TempDir()
+
+	tests := []struct {
+		name    string
+		content string
+	}{
+		{
+			name:    "missing id",
+			content: "type: http\nhttp:\n  paths: [\"/\"]\n",
+		},
+		{
+			name:    "missing type",
+			content: "id: no-type\nhttp:\n  paths: [\"/\"]\n",
+		},
+		{
+			name:    "malformed yaml",
+			content: "id: bad\ntype: http\n  paths: [unbalanced\n   : nope\n",
+		},
+		{
+			// a scalar where a mapping is expected must fail to unmarshal.
+			name:    "type mismatch",
+			content: "id: bad-shape\ntype: http\nhttp: \"should-be-a-map\"\n",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			path := writeModule(t, dir, tt.name+".yaml", tt.content)
+			if _, err := ParseYAMLModule(path); err == nil {
+				t.Fatalf("expected error for %s", tt.name)
+			}
+		})
+	}
+}
+
+func TestParseYAMLModuleMissingFile(t *testing.T) {
+	if _, err := ParseYAMLModule(filepath.Join(t.TempDir(), "does-not-exist.yaml")); err == nil {
+		t.Fatal("expected error for missing file")
+	}
+}
+
+func TestYAMLModuleWrapperInfoAndType(t *testing.T) {
+	def := &YAMLModule{
+		ID:   "wrap-test",
+		Type: TypeHTTP,
+		Info: YAMLModuleInfo{
+			Name:        "Wrapped",
+			Author:      "azzie",
+			Severity:    "low",
+			Description: "desc",
+			Tags:        []string{"a", "b"},
+		},
+	}
+	w := newYAMLModuleWrapper(def, "wrap.yaml")
+
+	if w.Type() != TypeHTTP {
+		t.Errorf("Type() = %q, want http", w.Type())
+	}
+	info := w.Info()
+	if info.ID != "wrap-test" || info.Name != "Wrapped" || info.Severity != "low" {
+		t.Errorf("Info() mismatch: %+v", info)
+	}
+	if len(info.Tags) != 2 {
+		t.Errorf("Info().Tags = %v, want 2 entries", info.Tags)
+	}
+}
+
+// TestLoaderLoadAll exercises the directory walk: a valid module registers, a
+// malformed one is skipped without aborting the walk.
+func TestLoaderLoadAll(t *testing.T) {
+	Clear()
+	t.Cleanup(Clear)
+
+	dir := t.TempDir()
+	writeModule(t, dir, "good.yaml", "id: good-mod\ntype: http\nhttp:\n  paths: [\"{{BaseURL}}/\"]\n  matchers:\n    - type: status\n      status: [200]\n")
+	writeModule(t, dir, "bad.yml", "id: bad-mod\n") // missing type -> skipped
+	writeModule(t, dir, "ignore.txt", "not a module")
+
+	l := &Loader{builtinDir: dir, userDir: filepath.Join(dir, "nonexistent-user")}
+	if err := l.LoadAll(); err != nil {
+		t.Fatalf("LoadAll: %v", err)
+	}
+
+	// only the good module loads; the malformed one is logged and skipped.
+	if l.Loaded() != 1 {
+		t.Errorf("Loaded() = %d, want 1", l.Loaded())
+	}
+	if _, ok := Get("good-mod"); !ok {
+		t.Error("good-mod not registered")
+	}
+	if _, ok := Get("bad-mod"); ok {
+		t.Error("bad-mod should not have registered")
+	}
+}
+
+func TestNewLoaderDirs(t *testing.T) {
+	l, err := NewLoader()
+	if err != nil {
+		t.Fatalf("NewLoader: %v", err)
+	}
+	if l.BuiltinDir() == "" {
+		t.Error("BuiltinDir is empty")
+	}
+	if l.UserDir() == "" {
+		t.Error("UserDir is empty")
+	}
+}
+
+// TestRegistry exercises the package-level registry: register, get, dedupe by
+// id, filter by tag and type, count and clear.
+func TestRegistry(t *testing.T) {
+	Clear()
+	t.Cleanup(Clear)
+
+	http1 := newYAMLModuleWrapper(&YAMLModule{ID: "h1", Type: TypeHTTP, Info: YAMLModuleInfo{Tags: []string{"web", "cve"}}}, "h1")
+	http2 := newYAMLModuleWrapper(&YAMLModule{ID: "h2", Type: TypeHTTP, Info: YAMLModuleInfo{Tags: []string{"web"}}}, "h2")
+	dns1 := newYAMLModuleWrapper(&YAMLModule{ID: "d1", Type: TypeDNS, Info: YAMLModuleInfo{Tags: []string{"dns"}}}, "d1")
+
+	Register(http1)
+	Register(http2)
+	Register(dns1)
+
+	if Count() != 3 {
+		t.Fatalf("Count() = %d, want 3", Count())
+	}
+
+	got, ok := Get("h1")
+	if !ok || got.Info().ID != "h1" {
+		t.Errorf("Get(h1) = %v, %v", got, ok)
+	}
+	if _, ok := Get("missing"); ok {
+		t.Error("Get(missing) should report not found")
+	}
+
+	if n := len(ByType(TypeHTTP)); n != 2 {
+		t.Errorf("ByType(http) = %d, want 2", n)
+	}
+	if n := len(ByType(TypeDNS)); n != 1 {
+		t.Errorf("ByType(dns) = %d, want 1", n)
+	}
+	if n := len(ByTag("web")); n != 2 {
+		t.Errorf("ByTag(web) = %d, want 2", n)
+	}
+	if n := len(ByTag("cve")); n != 1 {
+		t.Errorf("ByTag(cve) = %d, want 1", n)
+	}
+	if n := len(ByTag("none")); n != 0 {
+		t.Errorf("ByTag(none) = %d, want 0", n)
+	}
+	if n := len(All()); n != 3 {
+		t.Errorf("All() = %d, want 3", n)
+	}
+
+	// re-registering the same id overwrites rather than duplicating.
+	Register(newYAMLModuleWrapper(&YAMLModule{ID: "h1", Type: TypeHTTP}, "h1-v2"))
+	if Count() != 3 {
+		t.Errorf("Count() after re-register = %d, want 3", Count())
+	}
+
+	Clear()
+	if Count() != 0 {
+		t.Errorf("Count() after Clear = %d, want 0", Count())
+	}
+}
+
+// TestResultType pins the ScanResult interface bridge.
+func TestResultType(t *testing.T) {
+	r := &Result{ModuleID: "abc"}
+	if r.ResultType() != "abc" {
+		t.Errorf("ResultType() = %q, want abc", r.ResultType())
+	}
+}
+
+// TestLoaderScriptStubNoop confirms the go-script loader is currently a no-op
+// that registers nothing and returns no error.
+func TestLoaderScriptStubNoop(t *testing.T) {
+	l := &Loader{}
+	if err := l.loadScript("anything.go"); err != nil {
+		t.Errorf("loadScript stub returned error: %v", err)
+	}
+}

internal/modules/login_panels_test.go

@@ -0,0 +1,106 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runLoginModule(t *testing.T, file string, status int, headers map[string]string, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		for k, v := range headers {
+			w.Header().Set(k, v)
+		}
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func loginExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestLoginPanelModules(t *testing.T) {
+	const grafana = "../../modules/info/grafana-panel.yaml"
+	const kibana = "../../modules/info/kibana-panel.yaml"
+	const jenkins = "../../modules/info/jenkins-panel.yaml"
+
+	grafanaBody := `<body class="app-grafana"><grafana-app></grafana-app>` +
+		`<script>window.grafanaBootData = {"settings":{"buildInfo":{"version":"10.4.2","commit":"abc"}}};</script></body>`
+	kibanaBody := `<div data-test-subj="kibanaChrome"><kbn-injected-metadata data="x"></kbn-injected-metadata></div>`
+
+	t.Run("grafana login", func(t *testing.T) {
+		res := runLoginModule(t, grafana, 200, nil, grafanaBody)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a grafana finding")
+		}
+		if v := loginExtract(res, "grafana_version"); v != "10.4.2" {
+			t.Errorf("grafana_version=%q, want 10.4.2", v)
+		}
+	})
+
+	t.Run("kibana via response headers", func(t *testing.T) {
+		res := runLoginModule(t, kibana, 200, map[string]string{"kbn-version": "8.13.0", "kbn-name": "node-1"}, kibanaBody)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a kibana finding")
+		}
+		if v := loginExtract(res, "kibana_version"); v != "8.13.0" {
+			t.Errorf("kibana_version=%q, want 8.13.0", v)
+		}
+	})
+
+	t.Run("jenkins via X-Jenkins header on a 403", func(t *testing.T) {
+		res := runLoginModule(t, jenkins, 403, map[string]string{"X-Jenkins": "2.426.1"},
+			`<html><head><title>Authentication required</title></head></html>`)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a jenkins finding")
+		}
+		if v := loginExtract(res, "jenkins_version"); v != "2.426.1" {
+			t.Errorf("jenkins_version=%q, want 2.426.1", v)
+		}
+	})
+
+	t.Run("unrelated page is not a panel", func(t *testing.T) {
+		for _, file := range []string{grafana, kibana, jenkins} {
+			if res := runLoginModule(t, file, 200, nil, "<html><body>plain</body></html>"); len(res.Findings) > 0 {
+				t.Errorf("%s: unrelated page should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/management_api_exposure_test.go

@@ -0,0 +1,155 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runMgmtModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func mgmtExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestManagementAPIExposureModules(t *testing.T) {
+	const kong = "../../modules/recon/kong-api-exposure.yaml"
+	const jolokia = "../../modules/recon/jolokia-api-exposure.yaml"
+	const nats = "../../modules/recon/nats-api-exposure.yaml"
+
+	kongRoot := `{"version":"3.4.0","tagline":"Welcome to kong","hostname":"kong-node","node_id":"abc",` +
+		`"lua_version":"LuaJIT 2.1.0","plugins":{"available_on_server":{}},` +
+		`"configuration":{"database":"postgres","admin_listen":["0.0.0.0:8001"]}}`
+
+	jolokiaVersion := `{"request":{"type":"version"},"value":{"agent":"1.7.2","protocol":"7.2",` +
+		`"config":{"agentType":"servlet"},"info":{"product":"tomcat"}},"status":200,"timestamp":1694598949}`
+
+	natsVarz := `{"server_id":"NDABC","server_name":"NDABC","version":"2.10.1","proto":1,"go":"go1.21.1",` +
+		`"host":"0.0.0.0","port":4222,"max_connections":65536,"max_payload":1048576,"connections":3,"total_connections":10}`
+
+	t.Run("an exposed kong admin api is flagged and versioned", func(t *testing.T) {
+		res := runMgmtModule(t, kong, 200, kongRoot)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a kong finding")
+		}
+		if v := mgmtExtract(res, "kong_version"); v != "3.4.0" {
+			t.Errorf("kong_version=%q, want 3.4.0", v)
+		}
+	})
+
+	t.Run("an exposed jolokia agent is flagged and versioned", func(t *testing.T) {
+		res := runMgmtModule(t, jolokia, 200, jolokiaVersion)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a jolokia finding")
+		}
+		if v := mgmtExtract(res, "jolokia_agent_version"); v != "1.7.2" {
+			t.Errorf("jolokia_agent_version=%q, want 1.7.2", v)
+		}
+	})
+
+	t.Run("an exposed nats monitor is flagged and versioned", func(t *testing.T) {
+		res := runMgmtModule(t, nats, 200, natsVarz)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a nats finding")
+		}
+		if v := mgmtExtract(res, "nats_version"); v != "2.10.1" {
+			t.Errorf("nats_version=%q, want 2.10.1", v)
+		}
+	})
+
+	t.Run("an available plugins map without an admin listen is not flagged", func(t *testing.T) {
+		body := `{"plugins":{"available_on_server":{}},"version":"3.4.0"}`
+		if res := runMgmtModule(t, kong, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an available plugins map alone should not match kong, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an admin listen without an available plugins map is not flagged", func(t *testing.T) {
+		body := `{"configuration":{"admin_listen":["0.0.0.0:8001"]},"version":"1.0"}`
+		if res := runMgmtModule(t, kong, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an admin listen alone should not match kong, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a jolokia agent without a protocol is not flagged", func(t *testing.T) {
+		body := `{"value":{"agent":"1.7.2"}}`
+		if res := runMgmtModule(t, jolokia, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an agent alone should not match jolokia, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a jolokia protocol without an agent is not flagged", func(t *testing.T) {
+		body := `{"value":{"protocol":"7.2"},"info":{}}`
+		if res := runMgmtModule(t, jolokia, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a protocol alone should not match jolokia, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a nats server id without a max payload is not flagged", func(t *testing.T) {
+		body := `{"server_id":"NDABC","version":"2.10.1"}`
+		if res := runMgmtModule(t, nats, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a server id alone should not match nats, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a max payload without a nats server id is not flagged", func(t *testing.T) {
+		body := `{"max_payload":1048576,"port":4222}`
+		if res := runMgmtModule(t, nats, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a max payload alone should not match nats, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic version json is not a management api", func(t *testing.T) {
+		body := `{"version":"1.0.0","name":"app"}`
+		for _, file := range []string{kong, jolokia, nats} {
+			if res := runMgmtModule(t, file, 200, body); len(res.Findings) > 0 {
+				t.Errorf("%s: a generic version should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{kong, jolokia, nats} {
+			if res := runMgmtModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{kong, jolokia, nats} {
+			if res := runMgmtModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/matchers_condition_test.go

@@ -0,0 +1,132 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/dropalldatabases/sif/internal/httpx"
+)
+
+func TestCheckMatchersCondition(t *testing.T) {
+	const body = "hello world"
+	resp := fakeResponse(t, 200, nil)
+
+	status200 := Matcher{Type: "status", Status: []int{200}}
+	status500 := Matcher{Type: "status", Status: []int{500}}
+	wordHit := Matcher{Type: "word", Part: "body", Words: []string{"hello"}}
+	wordMiss := Matcher{Type: "word", Part: "body", Words: []string{"absent"}}
+
+	tests := []struct {
+		name      string
+		condition string
+		matchers  []Matcher
+		expect    bool
+	}{
+		{"and both match", "and", []Matcher{status200, wordHit}, true},
+		{"and one fails", "and", []Matcher{status200, wordMiss}, false},
+		{"empty defaults to and", "", []Matcher{status200, wordMiss}, false},
+		{"or one matches", "or", []Matcher{status500, wordHit}, true},
+		{"or none match", "or", []Matcher{status500, wordMiss}, false},
+		{"or all match", "or", []Matcher{status200, wordHit}, true},
+		{"or is case-insensitive", "OR", []Matcher{status500, wordHit}, true},
+		{"and is case-insensitive", "AND", []Matcher{status200, wordMiss}, false},
+		{"or with negative pass", "or", []Matcher{{Type: "word", Part: "body", Words: []string{"absent"}, Negative: true}}, true},
+		{"or all fail with negative", "or", []Matcher{{Type: "word", Part: "body", Words: []string{"hello"}, Negative: true}, wordMiss}, false},
+		{"empty matcher list", "or", nil, false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := checkMatchers(tt.matchers, tt.condition, resp, body); got != tt.expect {
+				t.Errorf("checkMatchers(%q) = %v, want %v", tt.condition, got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestValidateMatchersCondition(t *testing.T) {
+	for _, ok := range []string{"", "and", "or", "AND", "Or"} {
+		if err := validateMatchersCondition(ok); err != nil {
+			t.Errorf("%q should be valid: %v", ok, err)
+		}
+	}
+	for _, bad := range []string{"xor", "nand", "any", "&&"} {
+		if err := validateMatchersCondition(bad); err == nil {
+			t.Errorf("%q should be rejected", bad)
+		}
+	}
+}
+
+func TestParseMatchersConditionValidation(t *testing.T) {
+	write := func(cond string) string {
+		p := filepath.Join(t.TempDir(), "m.yaml")
+		body := fmt.Sprintf("id: mc\ntype: http\nhttp:\n  method: GET\n  paths: [\"{{BaseURL}}\"]\n  matchers-condition: %s\n  matchers:\n    - type: status\n      status: [200]\n", cond)
+		if err := os.WriteFile(p, []byte(body), 0o600); err != nil {
+			t.Fatal(err)
+		}
+		return p
+	}
+	if _, err := ParseYAMLModule(write("or")); err != nil {
+		t.Errorf("matchers-condition: or should parse: %v", err)
+	}
+	if _, err := ParseYAMLModule(write("xor")); err == nil {
+		t.Error("matchers-condition: xor should be rejected at load")
+	}
+}
+
+// or fires on the word match alone; and does not (status:500 fails).
+func TestExecuteHTTPModuleMatchersConditionOr(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		_, _ = w.Write([]byte("hello"))
+	}))
+	defer srv.Close()
+
+	def := &YAMLModule{
+		ID:   "mc",
+		Type: TypeHTTP,
+		Info: YAMLModuleInfo{Severity: "info"},
+		HTTP: &HTTPConfig{
+			Method: "GET",
+			Paths:  []string{"{{BaseURL}}/"},
+			Matchers: []Matcher{
+				{Type: "status", Status: []int{500}},
+				{Type: "word", Part: "body", Words: []string{"hello"}},
+			},
+		},
+	}
+	opts := Options{Timeout: testTimeout, Client: httpx.Client(testTimeout)}
+
+	def.HTTP.MatchersCondition = "or"
+	res, err := ExecuteHTTPModule(context.Background(), srv.URL, def, opts)
+	if err != nil {
+		t.Fatalf("or: %v", err)
+	}
+	if len(res.Findings) != 1 {
+		t.Fatalf("or: got %d findings, want 1", len(res.Findings))
+	}
+
+	def.HTTP.MatchersCondition = ""
+	res, err = ExecuteHTTPModule(context.Background(), srv.URL, def, opts)
+	if err != nil {
+		t.Fatalf("and: %v", err)
+	}
+	if len(res.Findings) != 0 {
+		t.Fatalf("and: got %d findings, want 0 (status:500 fails)", len(res.Findings))
+	}
+}

internal/modules/matchers_test.go

@@ -0,0 +1,531 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules
+
+import (
+	"net/http"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// fakeResponse builds a minimal *http.Response for matcher/extractor tests.
+// it carries no real socket (Body is http.NoBody), so there is nothing to
+// close; bodyclose is excluded for test files in .golangci.yml. header drives
+// the header/all parts without a live server; matchers read the body string
+// argument, not resp.Body.
+func fakeResponse(t *testing.T, status int, header http.Header) *http.Response {
+	t.Helper()
+	if header == nil {
+		header = http.Header{}
+	}
+	return &http.Response{StatusCode: status, Header: header, Body: http.NoBody}
+}
+
+func TestCheckMatcherStatus(t *testing.T) {
+	tests := []struct {
+		name   string
+		status int
+		want   []int
+		expect bool
+	}{
+		{name: "single match", status: 200, want: []int{200}, expect: true},
+		{name: "one of many", status: 404, want: []int{200, 301, 404}, expect: true},
+		{name: "no match", status: 500, want: []int{200, 404}, expect: false},
+		{name: "empty status list", status: 200, want: nil, expect: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			m := &Matcher{Type: "status", Status: tt.want}
+			resp := fakeResponse(t, tt.status, nil)
+			if got := checkMatcher(m, resp, ""); got != tt.expect {
+				t.Errorf("checkMatcher status = %v, want %v", got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestCheckMatcherWord(t *testing.T) {
+	const body = "welcome admin dashboard"
+
+	tests := []struct {
+		name      string
+		words     []string
+		condition string
+		expect    bool
+	}{
+		{name: "and all present", words: []string{"admin", "dashboard"}, condition: "and", expect: true},
+		{name: "and one missing", words: []string{"admin", "missing"}, condition: "and", expect: false},
+		{name: "default is and", words: []string{"admin", "missing"}, condition: "", expect: false},
+		{name: "or one present", words: []string{"missing", "admin"}, condition: "or", expect: true},
+		{name: "or none present", words: []string{"missing", "absent"}, condition: "or", expect: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			m := &Matcher{Type: "word", Part: "body", Words: tt.words, Condition: tt.condition}
+			resp := fakeResponse(t, 200, nil)
+			if got := checkMatcher(m, resp, body); got != tt.expect {
+				t.Errorf("checkMatcher word = %v, want %v", got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestCheckMatcherRegex(t *testing.T) {
+	const body = "version 1.2.3 build 99"
+
+	tests := []struct {
+		name      string
+		patterns  []string
+		condition string
+		expect    bool
+	}{
+		{name: "and all match", patterns: []string{`version \d`, `build \d+`}, condition: "and", expect: true},
+		{name: "and one fails", patterns: []string{`version \d`, `nope\d`}, condition: "and", expect: false},
+		{name: "or one matches", patterns: []string{`nope`, `build \d+`}, condition: "or", expect: true},
+		{name: "or none match", patterns: []string{`nope`, `zilch`}, condition: "or", expect: false},
+		// an invalid pattern under AND must fail closed, not panic.
+		{name: "and invalid pattern fails closed", patterns: []string{`version \d`, `(`}, condition: "and", expect: false},
+		// under OR an invalid pattern is skipped, a later valid one can still hit.
+		{name: "or invalid pattern skipped", patterns: []string{`(`, `build \d+`}, condition: "or", expect: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			m := &Matcher{Type: "regex", Part: "body", Regex: tt.patterns, Condition: tt.condition}
+			resp := fakeResponse(t, 200, nil)
+			if got := checkMatcher(m, resp, body); got != tt.expect {
+				t.Errorf("checkMatcher regex = %v, want %v", got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestCheckMatcherHeaderPart(t *testing.T) {
+	header := http.Header{"X-Powered-By": []string{"PHP/8.1"}}
+	resp := fakeResponse(t, 200, header)
+
+	m := &Matcher{Type: "word", Part: "header", Words: []string{"PHP/8.1"}}
+	if !checkMatcher(m, resp, "body-content") {
+		t.Error("expected header-part word matcher to hit on header value")
+	}
+
+	// the same word lives only in the header, so a body-part matcher must miss.
+	mBody := &Matcher{Type: "word", Part: "body", Words: []string{"PHP/8.1"}}
+	if checkMatcher(mBody, resp, "body-content") {
+		t.Error("body-part matcher should not see header-only value")
+	}
+}
+
+func TestCheckMatcherUnknownType(t *testing.T) {
+	m := &Matcher{Type: "size", Part: "body"}
+	resp := fakeResponse(t, 200, nil)
+	if checkMatcher(m, resp, "anything") {
+		t.Error("unknown matcher type should not match")
+	}
+}
+
+func TestCheckMatchers(t *testing.T) {
+	resp := fakeResponse(t, 200, http.Header{"Server": []string{"nginx"}})
+	const body = "secret token here"
+
+	tests := []struct {
+		name     string
+		matchers []Matcher
+		expect   bool
+	}{
+		{
+			name:     "empty matchers never match",
+			matchers: nil,
+			expect:   false,
+		},
+		{
+			name: "all matchers pass (AND across matchers)",
+			matchers: []Matcher{
+				{Type: "status", Status: []int{200}},
+				{Type: "word", Part: "body", Words: []string{"secret"}},
+			},
+			expect: true,
+		},
+		{
+			name: "one matcher fails breaks AND",
+			matchers: []Matcher{
+				{Type: "status", Status: []int{200}},
+				{Type: "word", Part: "body", Words: []string{"absent"}},
+			},
+			expect: false,
+		},
+		{
+			name: "negative inverts a non-match into a pass",
+			matchers: []Matcher{
+				{Type: "word", Part: "body", Words: []string{"absent"}, Negative: true},
+			},
+			expect: true,
+		},
+		{
+			name: "negative inverts a match into a fail",
+			matchers: []Matcher{
+				{Type: "word", Part: "body", Words: []string{"secret"}, Negative: true},
+			},
+			expect: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := checkMatchers(tt.matchers, "", resp, body); got != tt.expect {
+				t.Errorf("checkMatchers = %v, want %v", got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestCheckWords(t *testing.T) {
+	const content = "alpha beta gamma"
+
+	tests := []struct {
+		name      string
+		words     []string
+		condition string
+		expect    bool
+	}{
+		{name: "and all present", words: []string{"alpha", "gamma"}, condition: "and", expect: true},
+		{name: "and missing", words: []string{"alpha", "delta"}, condition: "and", expect: false},
+		{name: "or present", words: []string{"delta", "beta"}, condition: "or", expect: true},
+		{name: "or absent", words: []string{"delta", "epsilon"}, condition: "or", expect: false},
+		{name: "empty under and matches vacuously", words: nil, condition: "and", expect: true},
+		{name: "empty under or matches nothing", words: nil, condition: "or", expect: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := checkWords(content, tt.words, tt.condition); got != tt.expect {
+				t.Errorf("checkWords = %v, want %v", got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestCheckRegex(t *testing.T) {
+	const content = "id=42 name=root"
+
+	tests := []struct {
+		name      string
+		patterns  []string
+		condition string
+		expect    bool
+	}{
+		{name: "and all match", patterns: []string{`id=\d+`, `name=\w+`}, condition: "and", expect: true},
+		{name: "and one fails", patterns: []string{`id=\d+`, `zzz`}, condition: "and", expect: false},
+		{name: "or first matches", patterns: []string{`id=\d+`, `zzz`}, condition: "or", expect: true},
+		{name: "or none match", patterns: []string{`xxx`, `zzz`}, condition: "or", expect: false},
+		{name: "and bad regex fails closed", patterns: []string{`(`}, condition: "and", expect: false},
+		{name: "or bad regex skipped then match", patterns: []string{`(`, `name=\w+`}, condition: "or", expect: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := checkRegex(content, tt.patterns, tt.condition); got != tt.expect {
+				t.Errorf("checkRegex = %v, want %v", got, tt.expect)
+			}
+		})
+	}
+}
+
+func TestGetPart(t *testing.T) {
+	header := http.Header{"Server": []string{"nginx"}}
+	resp := fakeResponse(t, 200, header)
+	const body = "page body"
+
+	if got := getPart("body", resp, body); got != body {
+		t.Errorf("getPart body = %q, want %q", got, body)
+	}
+
+	headerPart := getPart("header", resp, body)
+	if !strings.Contains(headerPart, "Server") || !strings.Contains(headerPart, "nginx") {
+		t.Errorf("getPart header = %q, want it to include the header", headerPart)
+	}
+	if strings.Contains(headerPart, body) {
+		t.Errorf("getPart header should not include body, got %q", headerPart)
+	}
+
+	all := getPart("all", resp, body)
+	if !strings.Contains(all, "nginx") || !strings.Contains(all, body) {
+		t.Errorf("getPart all = %q, want both header and body", all)
+	}
+
+	// an unrecognised part falls back to the body.
+	if got := getPart("weird", resp, body); got != body {
+		t.Errorf("getPart fallback = %q, want body %q", got, body)
+	}
+
+	// empty part behaves like "all".
+	if got := getPart("", resp, body); !strings.Contains(got, "nginx") || !strings.Contains(got, body) {
+		t.Errorf("getPart empty = %q, want both header and body", got)
+	}
+}
+
+func TestRunExtractors(t *testing.T) {
+	resp := fakeResponse(t, 200, http.Header{"X-Token": []string{"abc123"}})
+	const body = `{"session":"sess-7788","role":"admin"}`
+
+	tests := []struct {
+		name       string
+		extractors []Extractor
+		wantKey    string
+		wantVal    string
+		wantNil    bool
+	}{
+		{
+			name:       "no extractors yields nil",
+			extractors: nil,
+			wantNil:    true,
+		},
+		{
+			name: "regex capture group on body",
+			extractors: []Extractor{
+				{Type: "regex", Name: "session", Part: "body", Regex: []string{`"session":"([^"]+)"`}, Group: 1},
+			},
+			wantKey: "session",
+			wantVal: "sess-7788",
+		},
+		{
+			name: "group zero is the whole match",
+			extractors: []Extractor{
+				{Type: "regex", Name: "role", Part: "body", Regex: []string{`role":"admin`}, Group: 0},
+			},
+			wantKey: "role",
+			wantVal: `role":"admin`,
+		},
+		{
+			name: "extract from header part",
+			extractors: []Extractor{
+				{Type: "regex", Name: "token", Part: "header", Regex: []string{`X-Token: (\S+)`}, Group: 1},
+			},
+			wantKey: "token",
+			wantVal: "abc123",
+		},
+		{
+			name: "first matching pattern wins",
+			extractors: []Extractor{
+				{Type: "regex", Name: "session", Part: "body", Regex: []string{`nomatch(\d+)`, `"session":"([^"]+)"`}, Group: 1},
+			},
+			wantKey: "session",
+			wantVal: "sess-7788",
+		},
+		{
+			name: "group index out of range is skipped",
+			extractors: []Extractor{
+				{Type: "regex", Name: "session", Part: "body", Regex: []string{`"session":"([^"]+)"`}, Group: 5},
+			},
+			wantNil: true,
+		},
+		{
+			name: "invalid pattern is skipped, no capture",
+			extractors: []Extractor{
+				{Type: "regex", Name: "session", Part: "body", Regex: []string{`(`}, Group: 1},
+			},
+			wantNil: true,
+		},
+		{
+			name: "unknown extractor type is ignored",
+			extractors: []Extractor{
+				{Type: "bogus", Name: "session", Part: "body", Regex: []string{`"session":"([^"]+)"`}, Group: 1},
+			},
+			wantNil: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := runExtractors(tt.extractors, resp, body)
+			if tt.wantNil {
+				if len(got) != 0 {
+					t.Errorf("runExtractors = %v, want empty", got)
+				}
+				return
+			}
+			if got[tt.wantKey] != tt.wantVal {
+				t.Errorf("runExtractors[%q] = %q, want %q", tt.wantKey, got[tt.wantKey], tt.wantVal)
+			}
+		})
+	}
+}
+
+func TestSubstituteVariables(t *testing.T) {
+	tests := []struct {
+		name     string
+		template string
+		baseURL  string
+		payload  string
+		want     string
+	}{
+		{
+			name:     "baseurl both cases",
+			template: "{{BaseURL}}/x and {{baseurl}}/y",
+			baseURL:  "http://h",
+			want:     "http://h/x and http://h/y",
+		},
+		{
+			name:     "payload both cases",
+			template: "q={{payload}}&r={{Payload}}",
+			payload:  "<script>",
+			want:     "q=<script>&r=<script>",
+		},
+		{
+			name:     "combined base and payload",
+			template: "{{BaseURL}}/search?q={{payload}}",
+			baseURL:  "http://h",
+			payload:  "x",
+			want:     "http://h/search?q=x",
+		},
+		{
+			name:     "no placeholders untouched",
+			template: "/static/path",
+			baseURL:  "http://h",
+			want:     "/static/path",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := substituteVariables(tt.template, tt.baseURL, tt.payload); got != tt.want {
+				t.Errorf("substituteVariables = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestGenerateHTTPRequests(t *testing.T) {
+	t.Run("paths without payloads", func(t *testing.T) {
+		cfg := &HTTPConfig{
+			Paths: []string{"{{BaseURL}}/a", "{{BaseURL}}/b"},
+		}
+		// trailing slash on the target must be trimmed before substitution.
+		got, err := generateHTTPRequests("http://h/", cfg)
+		if err != nil {
+			t.Fatalf("generate: %v", err)
+		}
+		if len(got) != 2 {
+			t.Fatalf("got %d requests, want 2", len(got))
+		}
+		if got[0].Method != "GET" {
+			t.Errorf("default method = %q, want GET", got[0].Method)
+		}
+		if got[0].URL != "http://h/a" || got[1].URL != "http://h/b" {
+			t.Errorf("urls = %q,%q", got[0].URL, got[1].URL)
+		}
+	})
+
+	t.Run("payload expansion is path x payload", func(t *testing.T) {
+		cfg := &HTTPConfig{
+			Method:   "POST",
+			Paths:    []string{"{{BaseURL}}/q?x={{payload}}"},
+			Payloads: []string{"1", "2", "3"},
+			Body:     "data={{payload}}",
+		}
+		got, err := generateHTTPRequests("http://h", cfg)
+		if err != nil {
+			t.Fatalf("generate: %v", err)
+		}
+		if len(got) != 3 {
+			t.Fatalf("got %d requests, want 3", len(got))
+		}
+		for i, want := range []string{"1", "2", "3"} {
+			if got[i].Payload != want {
+				t.Errorf("req %d payload = %q, want %q", i, got[i].Payload, want)
+			}
+			if got[i].URL != "http://h/q?x="+want {
+				t.Errorf("req %d url = %q", i, got[i].URL)
+			}
+			if got[i].Body != "data="+want {
+				t.Errorf("req %d body = %q", i, got[i].Body)
+			}
+			if got[i].Method != "POST" {
+				t.Errorf("req %d method = %q, want POST", i, got[i].Method)
+			}
+		}
+	})
+
+	t.Run("multiple paths times multiple payloads", func(t *testing.T) {
+		cfg := &HTTPConfig{
+			Paths:    []string{"{{BaseURL}}/a", "{{BaseURL}}/b"},
+			Payloads: []string{"x", "y"},
+		}
+		got, err := generateHTTPRequests("http://h", cfg)
+		if err != nil {
+			t.Fatalf("generate: %v", err)
+		}
+		if len(got) != 4 {
+			t.Fatalf("got %d requests, want 4 (2 paths x 2 payloads)", len(got))
+		}
+	})
+
+	t.Run("wordlist expands {{word}} paths", func(t *testing.T) {
+		list := filepath.Join(t.TempDir(), "words.txt")
+		if err := os.WriteFile(list, []byte("admin\n\nconfig\nbackup\n"), 0o600); err != nil {
+			t.Fatal(err)
+		}
+		cfg := &HTTPConfig{
+			Paths:    []string{"{{BaseURL}}/{{word}}", "{{BaseURL}}/.git/HEAD"},
+			Wordlist: list,
+		}
+		got, err := generateHTTPRequests("http://h", cfg)
+		if err != nil {
+			t.Fatalf("generate: %v", err)
+		}
+		// 3 words (the blank line is skipped) fuzz the templated path, then the
+		// literal path passes through untouched.
+		want := []string{"http://h/admin", "http://h/config", "http://h/backup", "http://h/.git/HEAD"}
+		if len(got) != len(want) {
+			t.Fatalf("got %d requests, want %d", len(got), len(want))
+		}
+		for i, w := range want {
+			if got[i].URL != w {
+				t.Errorf("req %d url = %q, want %q", i, got[i].URL, w)
+			}
+		}
+	})
+
+	t.Run("wordlist crosses with payloads", func(t *testing.T) {
+		list := filepath.Join(t.TempDir(), "words.txt")
+		if err := os.WriteFile(list, []byte("a\nb\n"), 0o600); err != nil {
+			t.Fatal(err)
+		}
+		cfg := &HTTPConfig{
+			Paths:    []string{"{{BaseURL}}/{{word}}?q={{payload}}"},
+			Wordlist: list,
+			Payloads: []string{"1", "2", "3"},
+		}
+		got, err := generateHTTPRequests("http://h", cfg)
+		if err != nil {
+			t.Fatalf("generate: %v", err)
+		}
+		if len(got) != 6 {
+			t.Fatalf("got %d requests, want 6 (2 words x 3 payloads)", len(got))
+		}
+	})
+
+	t.Run("missing wordlist errors", func(t *testing.T) {
+		cfg := &HTTPConfig{
+			Paths:    []string{"{{BaseURL}}/{{word}}"},
+			Wordlist: filepath.Join(t.TempDir(), "nope.txt"),
+		}
+		if _, err := generateHTTPRequests("http://h", cfg); err == nil {
+			t.Fatal("want error for missing wordlist, got nil")
+		}
+	})
+}

internal/modules/metrics_exposure_test.go

@@ -0,0 +1,138 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runMetricsModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func metricsExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestMetricsExposureModules(t *testing.T) {
+	const netdata = "../../modules/recon/netdata-api-exposure.yaml"
+	const cadvisor = "../../modules/recon/cadvisor-api-exposure.yaml"
+
+	netdataInfo := `{"version":"v1.44.0","uid":"6c5c8a3f","mirrored_hosts":["localhost"],` +
+		`"mirrored_hosts_status":[{"guid":"6c5c8a3f","reachable":true}],"os_name":"Debian GNU/Linux",` +
+		`"cores_total":"8","total_disk_space":"512000000000"}`
+
+	cadvisorMachine := `{"num_cores":8,"num_physical_cores":4,"num_sockets":1,"cpu_frequency_khz":2904000,` +
+		`"memory_capacity":16777216000,"machine_id":"a1b2c3d4e5f60718293a4b5c6d7e8f90",` +
+		`"system_uuid":"4C4C4544-0042-3110-8044-B7C04F564432","boot_id":"f0e1d2c3"}`
+
+	t.Run("an exposed netdata info endpoint is flagged and versioned", func(t *testing.T) {
+		res := runMetricsModule(t, netdata, 200, netdataInfo)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a netdata finding")
+		}
+		if v := metricsExtract(res, "netdata_version"); v != "v1.44.0" {
+			t.Errorf("netdata_version=%q, want v1.44.0", v)
+		}
+	})
+
+	t.Run("an exposed cadvisor machine endpoint is flagged with the machine id", func(t *testing.T) {
+		res := runMetricsModule(t, cadvisor, 200, cadvisorMachine)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a cadvisor finding")
+		}
+		if v := metricsExtract(res, "cadvisor_machine_id"); v != "a1b2c3d4e5f60718293a4b5c6d7e8f90" {
+			t.Errorf("cadvisor_machine_id=%q, want the machine id", v)
+		}
+	})
+
+	t.Run("netdata mirrored hosts without cores total is not flagged", func(t *testing.T) {
+		body := `{"version":"v1.44.0","mirrored_hosts":["localhost"]}`
+		if res := runMetricsModule(t, netdata, 200, body); len(res.Findings) > 0 {
+			t.Errorf("mirrored hosts alone should not match netdata, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("netdata cores total without mirrored hosts is not flagged", func(t *testing.T) {
+		body := `{"version":"v1.44.0","cores_total":"8"}`
+		if res := runMetricsModule(t, netdata, 200, body); len(res.Findings) > 0 {
+			t.Errorf("cores total alone should not match netdata, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("cadvisor machine id without a cpu frequency is not flagged", func(t *testing.T) {
+		body := `{"machine_id":"a1b2c3d4e5f60718293a4b5c6d7e8f90","num_cores":8}`
+		if res := runMetricsModule(t, cadvisor, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a machine id alone should not match cadvisor, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("cadvisor cpu frequency without a machine id is not flagged", func(t *testing.T) {
+		body := `{"cpu_frequency_khz":2904000,"num_cores":8}`
+		if res := runMetricsModule(t, cadvisor, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a cpu frequency alone should not match cadvisor, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic metrics json is not netdata", func(t *testing.T) {
+		body := `{"status":"ok","data":{"result":[]}}`
+		if res := runMetricsModule(t, netdata, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic json should not match netdata, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{netdata, cadvisor} {
+			if res := runMetricsModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{netdata, cadvisor} {
+			if res := runMetricsModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/module.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
@@ -86,11 +86,13 @@ type Finding struct {
 // Matcher defines matching logic for module responses.
 // Matchers are used to determine if a response indicates a vulnerability.
 type Matcher struct {
-	Type      string   `yaml:"type"` // regex, status, word, size
+	Type      string   `yaml:"type"` // regex, status, word, favicon
 	Part      string   `yaml:"part"` // body, header, all
 	Regex     []string `yaml:"regex,omitempty"`
 	Words     []string `yaml:"words,omitempty"`
 	Status    []int    `yaml:"status,omitempty"`
+	Size      []int    `yaml:"size,omitempty"`
+	Hash      []int64  `yaml:"hash,omitempty"` // favicon: shodan mmh3 hashes (signed or unsigned)
 	Condition string   `yaml:"condition"` // and, or
 	Negative  bool     `yaml:"negative"`
 }
@@ -98,9 +100,10 @@ type Matcher struct {
 // Extractor defines data extraction from responses.
 // Extractors pull specific data from matched responses for reporting.
 type Extractor struct {
-	Type  string   `yaml:"type"` // regex, kval, json
+	Type  string   `yaml:"type"` // regex, kv, json
 	Name  string   `yaml:"name"`
 	Part  string   `yaml:"part"`
 	Regex []string `yaml:"regex,omitempty"`
+	JSON  []string `yaml:"json,omitempty"`
 	Group int      `yaml:"group"`
 }

internal/modules/ops_panels_test.go

@@ -0,0 +1,112 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+// runOpsModule runs a shipped module end to end against a server that returns
+// the same status and body for every path it requests.
+func runOpsModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func opsExtracted(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v, ok := f.Extracted[key]; ok {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestOpsPanelModules(t *testing.T) {
+	cases := []struct {
+		name        string
+		file        string
+		status      int
+		body        string
+		wantFinding bool
+		versionKey  string
+		versionVal  string
+	}{
+		{
+			name: "portainer status api", file: "../../modules/info/portainer-panel.yaml", status: 200,
+			body:        `{"Edition":"CE","Version":"2.19.4","InstanceID":"a1b2c3"}`,
+			wantFinding: true, versionKey: "portainer_version", versionVal: "2.19.4",
+		},
+		{
+			name: "portainer version-only json is not a match", file: "../../modules/info/portainer-panel.yaml", status: 200,
+			body: `{"Version":"1.0.0"}`, wantFinding: false,
+		},
+		{
+			name: "portainer real body behind a 404 is not a match", file: "../../modules/info/portainer-panel.yaml", status: 404,
+			body: `{"Edition":"CE","Version":"2.19.4","InstanceID":"a1b2c3"}`, wantFinding: false,
+		},
+		{
+			name: "traefik version api", file: "../../modules/info/traefik-panel.yaml", status: 200,
+			body:        `{"Version":"2.10.4","Codename":"saintnectaire","startDate":"2024-01-01T00:00:00Z"}`,
+			wantFinding: true, versionKey: "traefik_version", versionVal: "2.10.4",
+		},
+		{
+			name: "traefik without codename is not a match", file: "../../modules/info/traefik-panel.yaml", status: 200,
+			body: `{"Version":"2.10.4"}`, wantFinding: false,
+		},
+		{
+			name: "keycloak realm endpoint", file: "../../modules/info/keycloak-panel.yaml", status: 200,
+			body:        `{"realm":"master","public_key":"MIIBIjAN","token-service":"https://h/realms/master/protocol/openid-connect","account-service":"https://h/realms/master/account"}`,
+			wantFinding: true, versionKey: "keycloak_realm", versionVal: "master",
+		},
+		{
+			name: "keycloak partial realm json is not a match", file: "../../modules/info/keycloak-panel.yaml", status: 200,
+			body: `{"realm":"master","public_key":"MIIBIjAN"}`, wantFinding: false,
+		},
+		{
+			name: "rabbitmq management ui", file: "../../modules/info/rabbitmq-panel.yaml", status: 200,
+			body:        `<!DOCTYPE html><html><head><title>RabbitMQ Management</title></head><body><img src="img/rabbitmqlogo.svg"></body></html>`,
+			wantFinding: true,
+		},
+		{
+			name: "rabbitmq unrelated page is not a match", file: "../../modules/info/rabbitmq-panel.yaml", status: 200,
+			body: `<html><body>nothing to see</body></html>`, wantFinding: false,
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			res := runOpsModule(t, tc.file, tc.status, tc.body)
+			got := len(res.Findings) > 0
+			if got != tc.wantFinding {
+				t.Fatalf("findings=%d, want match=%v", len(res.Findings), tc.wantFinding)
+			}
+			if tc.versionKey != "" {
+				if v := opsExtracted(res, tc.versionKey); v != tc.versionVal {
+					t.Errorf("extracted[%q]=%q, want %q", tc.versionKey, v, tc.versionVal)
+				}
+			}
+		})
+	}
+}

internal/modules/orchestration_api_exposure_test.go

@@ -0,0 +1,132 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runOrchModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func orchExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestOrchestrationAPIExposureModules(t *testing.T) {
+	const vault = "../../modules/recon/vault-api-exposure.yaml"
+	const consul = "../../modules/recon/consul-api-exposure.yaml"
+	const etcd = "../../modules/recon/etcd-api-exposure.yaml"
+
+	vaultSeal := `{"type":"shamir","initialized":true,"sealed":false,"t":3,"n":5,` +
+		`"progress":0,"nonce":"","version":"1.15.2","build_date":"2023-11-06T11:33:49Z",` +
+		`"migration":false,"cluster_name":"vault-cluster-9d52b1f1","recovery_seal":false,` +
+		`"storage_type":"raft"}`
+
+	consulSelf := `{"Config":{"Datacenter":"dc1","NodeName":"consul-server-1","Server":true,` +
+		`"Version":"1.17.0"},"Member":{"Name":"consul-server-1","Addr":"10.0.0.5","Port":8301}}`
+
+	etcdVersion := `{"etcdserver":"3.5.9","etcdcluster":"3.5.0"}`
+
+	t.Run("an exposed vault seal-status is flagged and versioned", func(t *testing.T) {
+		res := runOrchModule(t, vault, 200, vaultSeal)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a vault finding")
+		}
+		if v := orchExtract(res, "vault_version"); v != "1.15.2" {
+			t.Errorf("vault_version=%q, want 1.15.2", v)
+		}
+	})
+
+	t.Run("an exposed consul agent self leaks the datacenter", func(t *testing.T) {
+		res := runOrchModule(t, consul, 200, consulSelf)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a consul finding")
+		}
+		if v := orchExtract(res, "consul_datacenter"); v != "dc1" {
+			t.Errorf("consul_datacenter=%q, want dc1", v)
+		}
+	})
+
+	t.Run("an exposed etcd version endpoint is flagged and versioned", func(t *testing.T) {
+		res := runOrchModule(t, etcd, 200, etcdVersion)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an etcd finding")
+		}
+		if v := orchExtract(res, "etcd_version"); v != "3.5.9" {
+			t.Errorf("etcd_version=%q, want 3.5.9", v)
+		}
+	})
+
+	t.Run("a sealed flag without the other vault keys is not vault", func(t *testing.T) {
+		body := `{"sealed":"yes","status":"ok"}`
+		if res := runOrchModule(t, vault, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a bare sealed flag should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a datacenter field alone is not consul", func(t *testing.T) {
+		body := `{"Datacenter":"dc1"}`
+		if res := runOrchModule(t, consul, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a bare datacenter field should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a version response from another service is not etcd", func(t *testing.T) {
+		body := `{"version":"1.2.3","service":"myapp"}`
+		if res := runOrchModule(t, etcd, 200, body); len(res.Findings) > 0 {
+			t.Errorf("another service version should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an etcdserver without an etcdcluster is not flagged", func(t *testing.T) {
+		body := `{"etcdserver":"3.5.9"}`
+		if res := runOrchModule(t, etcd, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a partial etcd response should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{vault, consul, etcd} {
+			if res := runOrchModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{vault, consul, etcd} {
+			if res := runOrchModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/rails_secret_exposure_test.go

@@ -0,0 +1,131 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runRailsModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func railsExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestRailsSecretExposureModules(t *testing.T) {
+	const database = "../../modules/recon/rails-database-yml-exposure.yaml"
+	const secrets = "../../modules/recon/rails-secrets-yml-exposure.yaml"
+	const masterKey = "../../modules/recon/rails-master-key-exposure.yaml"
+
+	const keyBase = "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef" +
+		"0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef"
+	const masterKeyValue = "0123456789abcdef0123456789abcdef"
+
+	t.Run("database config leaks the database name and credentials", func(t *testing.T) {
+		body := "default: &default\n  adapter: postgresql\n  encoding: unicode\n  pool: 5\n" +
+			"  username: app_user\n  password: s3cr3tdbpass\n  host: db.internal\n\n" +
+			"production:\n  <<: *default\n  database: myapp_production\n"
+		res := runRailsModule(t, database, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a database config finding")
+		}
+		if v := railsExtract(res, "database"); v != "myapp_production" {
+			t.Errorf("database=%q, want myapp_production", v)
+		}
+	})
+
+	t.Run("a credential free sqlite database config is not a leak", func(t *testing.T) {
+		body := "production:\n  adapter: sqlite3\n  database: db/production.sqlite3\n  pool: 5\n"
+		if res := runRailsModule(t, database, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a sqlite config without credentials should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("secrets config leaks the secret key base", func(t *testing.T) {
+		body := "development:\n  secret_key_base: " + keyBase + "\n"
+		res := runRailsModule(t, secrets, 200, body)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a secrets config finding")
+		}
+		if v := railsExtract(res, "secret_key_base"); v != keyBase {
+			t.Errorf("secret_key_base=%q, want %q", v, keyBase)
+		}
+	})
+
+	t.Run("master key file leaks the key", func(t *testing.T) {
+		res := runRailsModule(t, masterKey, 200, masterKeyValue)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a master key finding")
+		}
+		if v := railsExtract(res, "master_key"); v != masterKeyValue {
+			t.Errorf("master_key=%q, want %q", v, masterKeyValue)
+		}
+	})
+
+	t.Run("a longer hex digest is not the master key", func(t *testing.T) {
+		body := masterKeyValue + masterKeyValue
+		if res := runRailsModule(t, masterKey, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a 64 char digest should not match the 32 char key, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a hex value not at the body start is not the master key", func(t *testing.T) {
+		body := "key=" + masterKeyValue
+		if res := runRailsModule(t, masterKey, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a hex value away from the start should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page naming the rails markers is not a leak", func(t *testing.T) {
+		body := "<html><head><title>Error</title></head><body>secret_key_base: " + keyBase + "</body></html>"
+		if res := runRailsModule(t, secrets, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a config without the rails markers is not a leak", func(t *testing.T) {
+		body := "password: hunter2\nusername: admin\nhost: db.internal\n"
+		for _, file := range []string{database, secrets, masterKey} {
+			if res := runRailsModule(t, file, 200, body); len(res.Findings) > 0 {
+				t.Errorf("%s: a config without the rails markers should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{database, secrets, masterKey} {
+			if res := runRailsModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/registry.go

@@ -4,7 +4,7 @@
 :   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
 :   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
 :                                                                               :
-:   (c) 2022-2025 vmfunc (vmfunc), xyzeva,                        :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
 :                 lunchcat alumni & contributors                                :
 :                                                                               :
 ·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·

internal/modules/registry_exposure_test.go

@@ -0,0 +1,118 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runRegistryModule(t *testing.T, file string, status int, headers map[string]string, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		for k, v := range headers {
+			w.Header().Set(k, v)
+		}
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func registryExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestRegistryExposureModules(t *testing.T) {
+	const dockerRegistry = "../../modules/recon/docker-registry-api-exposure.yaml"
+	const harbor = "../../modules/recon/harbor-api-exposure.yaml"
+
+	registryHeader := map[string]string{"Docker-Distribution-Api-Version": "registry/2.0"}
+
+	harborInfo := `{"auth_mode":"db_auth","registry_url":"harbor.example.com",` +
+		`"external_url":"https://harbor.example.com","harbor_version":"v2.9.1-1f4a3c9d",` +
+		`"self_registration":true,"has_ca_root":false,"read_only":false}`
+
+	t.Run("an anonymous docker registry is flagged with its api version", func(t *testing.T) {
+		res := runRegistryModule(t, dockerRegistry, 200, registryHeader, "{}")
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a docker registry finding")
+		}
+		if v := registryExtract(res, "docker_registry_api_version"); v != "registry/2.0" {
+			t.Errorf("docker_registry_api_version=%q, want registry/2.0", v)
+		}
+	})
+
+	t.Run("a plain 200 without the registry header is not flagged", func(t *testing.T) {
+		if res := runRegistryModule(t, dockerRegistry, 200, nil, "{}"); len(res.Findings) > 0 {
+			t.Errorf("a 200 without the api-version header should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a registry that requires auth is not flagged", func(t *testing.T) {
+		if res := runRegistryModule(t, dockerRegistry, 401, registryHeader, ""); len(res.Findings) > 0 {
+			t.Errorf("a 401 registry should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an exposed harbor systeminfo is flagged and versioned", func(t *testing.T) {
+		res := runRegistryModule(t, harbor, 200, nil, harborInfo)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a harbor finding")
+		}
+		if v := registryExtract(res, "harbor_version"); v != "v2.9.1-1f4a3c9d" {
+			t.Errorf("harbor_version=%q, want v2.9.1-1f4a3c9d", v)
+		}
+	})
+
+	t.Run("a harbor version without an auth mode is not flagged", func(t *testing.T) {
+		body := `{"harbor_version":"v2.9.1","registry_url":"harbor.example.com"}`
+		if res := runRegistryModule(t, harbor, 200, nil, body); len(res.Findings) > 0 {
+			t.Errorf("a harbor version alone should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an auth mode without a harbor version is not flagged", func(t *testing.T) {
+		body := `{"auth_mode":"db_auth","self_registration":true}`
+		if res := runRegistryModule(t, harbor, 200, nil, body); len(res.Findings) > 0 {
+			t.Errorf("an auth mode alone should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{dockerRegistry, harbor} {
+			if res := runRegistryModule(t, file, 200, nil, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{dockerRegistry, harbor} {
+			if res := runRegistryModule(t, file, 404, nil, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/runtime_api_exposure_test.go

@@ -0,0 +1,175 @@
+/*
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+:                                                                               :
+:   █▀ █ █▀▀   ·   Blazing-fast pentesting suite                                :
+:   ▄█ █ █▀    ·   BSD 3-Clause License                                         :
+:                                                                               :
+:   (c) 2022-2026 vmfunc, xyzeva,                                               :
+:                 lunchcat alumni & contributors                                :
+:                                                                               :
+·━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━·
+*/
+
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runRuntimeModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func runtimeExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestRuntimeAPIExposureModules(t *testing.T) {
+	const docker = "../../modules/recon/docker-api-exposure.yaml"
+	const k8s = "../../modules/recon/kubernetes-api-exposure.yaml"
+	const kubelet = "../../modules/recon/kubelet-api-exposure.yaml"
+
+	dockerVersion := `{"Platform":{"Name":"Docker Engine - Community"},"Components":[` +
+		`{"Name":"Engine","Version":"24.0.7","Details":{"ApiVersion":"1.43"}},` +
+		`{"Name":"containerd","Version":"1.6.24"},{"Name":"runc","Version":"1.1.9"}],` +
+		`"Version":"24.0.7","ApiVersion":"1.43","MinAPIVersion":"1.12","GitCommit":"311b9ff",` +
+		`"GoVersion":"go1.20.10","Os":"linux","Arch":"amd64"}`
+
+	k8sVersion := `{"major":"1","minor":"28","gitVersion":"v1.28.2","gitCommit":"abc123",` +
+		`"gitTreeState":"clean","buildDate":"2023-09-13T09:35:49Z","goVersion":"go1.20.8",` +
+		`"compiler":"gc","platform":"linux/amd64"}`
+
+	kubeletPods := `{"kind":"PodList","apiVersion":"v1","metadata":{},"items":[{"metadata":` +
+		`{"name":"etcd-master","namespace":"kube-system"},"spec":{"containers":[{"name":"etcd"}]}}]}`
+
+	t.Run("an exposed docker api is flagged and versioned", func(t *testing.T) {
+		res := runRuntimeModule(t, docker, 200, dockerVersion)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a docker finding")
+		}
+		if v := runtimeExtract(res, "docker_version"); v != "24.0.7" {
+			t.Errorf("docker_version=%q, want 24.0.7", v)
+		}
+	})
+
+	t.Run("an exposed kubernetes api is flagged and versioned", func(t *testing.T) {
+		res := runRuntimeModule(t, k8s, 200, k8sVersion)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a kubernetes finding")
+		}
+		if v := runtimeExtract(res, "k8s_version"); v != "v1.28.2" {
+			t.Errorf("k8s_version=%q, want v1.28.2", v)
+		}
+	})
+
+	t.Run("an exposed kubelet leaks a pod namespace", func(t *testing.T) {
+		res := runRuntimeModule(t, kubelet, 200, kubeletPods)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a kubelet finding")
+		}
+		if v := runtimeExtract(res, "kubelet_namespace"); v != "kube-system" {
+			t.Errorf("kubelet_namespace=%q, want kube-system", v)
+		}
+	})
+
+	t.Run("a generic version json without the docker fields is not docker", func(t *testing.T) {
+		body := `{"version":"1.0.0","name":"myapp"}`
+		if res := runRuntimeModule(t, docker, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic version should not match docker, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an apiversion without a min api version is not docker", func(t *testing.T) {
+		body := `{"ApiVersion":"2.0","name":"otherservice"}`
+		if res := runRuntimeModule(t, docker, 200, body); len(res.Findings) > 0 {
+			t.Errorf("apiversion alone should not match docker, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a min api version without an api version is not docker", func(t *testing.T) {
+		body := `{"MinAPIVersion":"1.12","Os":"linux"}`
+		if res := runRuntimeModule(t, docker, 200, body); len(res.Findings) > 0 {
+			t.Errorf("min api version alone should not match docker, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic version json without the git fields is not kubernetes", func(t *testing.T) {
+		body := `{"version":"1.2.3","build":"xyz"}`
+		if res := runRuntimeModule(t, k8s, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic version should not match kubernetes, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a gitversion without a git tree state is not kubernetes", func(t *testing.T) {
+		body := `{"gitVersion":"v1.0.0","app":"custom"}`
+		if res := runRuntimeModule(t, k8s, 200, body); len(res.Findings) > 0 {
+			t.Errorf("gitversion alone should not match kubernetes, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a build date without a gitversion is not kubernetes", func(t *testing.T) {
+		body := `{"buildDate":"2023-01-01T00:00:00Z","app":"custom"}`
+		if res := runRuntimeModule(t, k8s, 200, body); len(res.Findings) > 0 {
+			t.Errorf("build date alone should not match kubernetes, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a service list is not a kubelet pod list", func(t *testing.T) {
+		body := `{"kind":"ServiceList","apiVersion":"v1","items":[]}`
+		if res := runRuntimeModule(t, kubelet, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a service list should not match kubelet, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a pod list without an api version is not flagged", func(t *testing.T) {
+		body := `{"kind":"PodList","items":[]}`
+		if res := runRuntimeModule(t, kubelet, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a pod list without apiversion should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{docker, k8s, kubelet} {
+			if res := runRuntimeModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{docker, k8s, kubelet} {
+			if res := runRuntimeModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/secret_file_exposure_test.go

@@ -0,0 +1,162 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runSecretModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func secretExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestSecretFileExposureModules(t *testing.T) {
+	const privkey = "../../modules/recon/private-key-exposure.yaml"
+	const gitcred = "../../modules/recon/git-credentials-exposure.yaml"
+	const pypirc = "../../modules/recon/pypirc-exposure.yaml"
+
+	opensshKey := "-----BEGIN OPENSSH PRIVATE KEY-----\n" +
+		"b3BlbnNzaC1rZXktdjEAAAAABG5vbmUAAAAEbm9uZQAAAAAAAAABAAAAMwAAAAtzc2gtZWQy\n" +
+		"NTUxOQAAACD1aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\n" +
+		"-----END OPENSSH PRIVATE KEY-----\n"
+
+	rsaKey := "-----BEGIN RSA PRIVATE KEY-----\n" +
+		"MIIEpAIBAAKCAQEArandombase64payloadthatstandsinforakeybodyhere1234567890\n" +
+		"-----END RSA PRIVATE KEY-----\n"
+
+	gitCreds := "https://octocat:ghp_AbCdEf0123456789AbCdEf0123456789@github.com\n" +
+		"https://deploy:s3cr3t@gitlab.example.com\n"
+
+	pypiConfig := "[distutils]\nindex-servers =\n    pypi\n\n[pypi]\n" +
+		"username = __token__\npassword = pypi-AgEIcHlwaS5vcmcCJDQ2Y2Q\n"
+
+	t.Run("an openssh private key is flagged and typed", func(t *testing.T) {
+		res := runSecretModule(t, privkey, 200, opensshKey)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a private key finding")
+		}
+		if v := secretExtract(res, "key_type"); v != "OPENSSH" {
+			t.Errorf("key_type=%q, want OPENSSH", v)
+		}
+	})
+
+	t.Run("an rsa private key is flagged and typed", func(t *testing.T) {
+		res := runSecretModule(t, privkey, 200, rsaKey)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a private key finding")
+		}
+		if v := secretExtract(res, "key_type"); v != "RSA" {
+			t.Errorf("key_type=%q, want RSA", v)
+		}
+	})
+
+	t.Run("a git credential store leaks its host", func(t *testing.T) {
+		res := runSecretModule(t, gitcred, 200, gitCreds)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a git credential finding")
+		}
+		if v := secretExtract(res, "git_host"); v != "github.com" {
+			t.Errorf("git_host=%q, want github.com", v)
+		}
+	})
+
+	t.Run("a pypirc leaks the upload token", func(t *testing.T) {
+		res := runSecretModule(t, pypirc, 200, pypiConfig)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a pypirc finding")
+		}
+		if v := secretExtract(res, "pypi_token"); v != "pypi-AgEIcHlwaS5vcmcCJDQ2Y2Q" {
+			t.Errorf("pypi_token=%q, want the pypi- token", v)
+		}
+	})
+
+	t.Run("a public key is not a private key", func(t *testing.T) {
+		body := "-----BEGIN PUBLIC KEY-----\nMFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBAK\n" +
+			"-----END PUBLIC KEY-----\nssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAAB user@host\n"
+		if res := runSecretModule(t, privkey, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a public key should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("prose that names a private key is not the key", func(t *testing.T) {
+		body := "Generate your private key with ssh-keygen and keep id_rsa secret."
+		if res := runSecretModule(t, privkey, 200, body); len(res.Findings) > 0 {
+			t.Errorf("prose about keys should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a git remote url without a password is not a credential store", func(t *testing.T) {
+		body := "https://github.com/octocat/hello-world.git\n"
+		if res := runSecretModule(t, gitcred, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a bare remote url should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a pypi section without a credential is not a leak", func(t *testing.T) {
+		body := "[distutils]\nindex-servers =\n    pypi\n"
+		if res := runSecretModule(t, pypirc, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a section with no credential should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("credentials shown in an html page are not a store", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body>clone with https://user:pass@host.example</body></html>"
+		if res := runSecretModule(t, gitcred, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a pypi config inside an html page is not a leak", func(t *testing.T) {
+		body := "<html><head><title>docs</title></head><body><pre>[pypi]\npassword = pypi-x</pre></body></html>"
+		if res := runSecretModule(t, pypirc, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{privkey, gitcred, pypirc} {
+			if res := runSecretModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{privkey, gitcred, pypirc} {
+			if res := runSecretModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}

internal/modules/vcs_metadata_exposure_test.go

@@ -0,0 +1,155 @@
+package modules_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/dropalldatabases/sif/internal/modules"
+)
+
+func runVCSModule(t *testing.T, file string, status int, body string) *modules.Result {
+	t.Helper()
+	def, err := modules.ParseYAMLModule(file)
+	if err != nil {
+		t.Fatalf("parse %s: %v", file, err)
+	}
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(status)
+		_, _ = w.Write([]byte(body))
+	}))
+	defer srv.Close()
+
+	res, err := modules.ExecuteHTTPModule(context.Background(), srv.URL, def, modules.Options{
+		Timeout: 5 * time.Second,
+		Threads: 2,
+	})
+	if err != nil {
+		t.Fatalf("execute %s: %v", file, err)
+	}
+	return res
+}
+
+func vcsExtract(res *modules.Result, key string) string {
+	for _, f := range res.Findings {
+		if v := f.Extracted[key]; v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func TestVCSMetadataExposureModules(t *testing.T) {
+	const svn = "../../modules/recon/svn-exposure.yaml"
+	const hg = "../../modules/recon/mercurial-exposure.yaml"
+	const bzr = "../../modules/recon/bazaar-exposure.yaml"
+
+	svnWcDb := "SQLite format 3\x00" + strings.Repeat("\x00", 80) +
+		"CREATE TABLE WCROOT (id INTEGER PRIMARY KEY);" +
+		"CREATE TABLE REPOSITORY (root TEXT, uuid TEXT);" +
+		"\x01root\x00https://svn.example.com/myrepo/trunk\x00"
+
+	hgRequires := "revlogv1\nstore\nfncache\ndotencode\ngeneraldelta\nsparserevlog\n"
+
+	bzrFormat := "Bazaar-NG meta directory, format 1\n"
+
+	t.Run("an exposed svn wc.db leaks the repository url", func(t *testing.T) {
+		res := runVCSModule(t, svn, 200, svnWcDb)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected an svn finding")
+		}
+		if v := vcsExtract(res, "svn_repository"); v != "https://svn.example.com/myrepo/trunk" {
+			t.Errorf("svn_repository=%q, want https://svn.example.com/myrepo/trunk", v)
+		}
+	})
+
+	t.Run("an exposed mercurial requires is flagged", func(t *testing.T) {
+		res := runVCSModule(t, hg, 200, hgRequires)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a mercurial finding")
+		}
+		if v := vcsExtract(res, "hg_requirement"); v != "revlogv1" {
+			t.Errorf("hg_requirement=%q, want revlogv1", v)
+		}
+	})
+
+	t.Run("an exposed bazaar branch-format is flagged", func(t *testing.T) {
+		res := runVCSModule(t, bzr, 200, bzrFormat)
+		if len(res.Findings) == 0 {
+			t.Fatal("expected a bazaar finding")
+		}
+		if v := vcsExtract(res, "bzr_format"); v != "Bazaar-NG meta directory, format 1" {
+			t.Errorf("bzr_format=%q, want the meta directory signature", v)
+		}
+	})
+
+	t.Run("a generic sqlite database without svn tables is not flagged", func(t *testing.T) {
+		body := "SQLite format 3\x00" + strings.Repeat("\x00", 80) +
+			"CREATE TABLE users (id INTEGER, name TEXT, email TEXT);"
+		if res := runVCSModule(t, svn, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic sqlite db should not match svn, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a generic sqlite with a nodes table is not an svn working copy", func(t *testing.T) {
+		body := "SQLite format 3\x00" + strings.Repeat("\x00", 80) +
+			"CREATE TABLE NODES (id INTEGER PRIMARY KEY, parent INTEGER, label TEXT);"
+		if res := runVCSModule(t, svn, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a generic nodes table should not match svn, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an svn magic that is not at byte zero is not flagged", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>SQLite format 3 WCROOT REPOSITORY</pre></body></html>"
+		if res := runVCSModule(t, svn, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an unanchored magic should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a page naming mercurial without the requires format is not flagged", func(t *testing.T) {
+		body := "this project uses mercurial for distributed version control"
+		if res := runVCSModule(t, hg, 200, body); len(res.Findings) > 0 {
+			t.Errorf("prose naming mercurial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating hg requires is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>revlogv1\nstore\ndotencode</pre></body></html>"
+		if res := runVCSModule(t, hg, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html hg tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a bazaar marketplace page is not a repository", func(t *testing.T) {
+		body := "Welcome to the Bazaar, the finest open air marketplace in town"
+		if res := runVCSModule(t, bzr, 200, body); len(res.Findings) > 0 {
+			t.Errorf("a marketplace page should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("an html page demonstrating bzr branch-format is not a leak", func(t *testing.T) {
+		body := "<!DOCTYPE html><html><body><pre>Bazaar-NG meta directory, format 1</pre></body></html>"
+		if res := runVCSModule(t, bzr, 200, body); len(res.Findings) > 0 {
+			t.Errorf("an html bzr tutorial should not match, got %d findings", len(res.Findings))
+		}
+	})
+
+	t.Run("a plain 200 body is not a leak", func(t *testing.T) {
+		for _, file := range []string{svn, hg, bzr} {
+			if res := runVCSModule(t, file, 200, "ok"); len(res.Findings) > 0 {
+				t.Errorf("%s: a plain 200 body should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+
+	t.Run("a 404 is not a leak", func(t *testing.T) {
+		for _, file := range []string{svn, hg, bzr} {
+			if res := runVCSModule(t, file, 404, "not found"); len(res.Findings) > 0 {
+				t.Errorf("%s: a 404 should not match, got %d findings", file, len(res.Findings))
+			}
+		}
+	})
+}