mirror of
https://github.com/lunchcat/sif.git
synced 2026-07-28 14:37:01 -07:00
modules/recon/airflow-api-exposure.yaml flags an exposed Apache Airflow webserver through its unauthenticated health endpoint, keyed on the metadatabase and scheduler health blocks, then extracts the scheduler heartbeat. modules/recon/flink-api-exposure.yaml flags an exposed Apache Flink dashboard, keyed on the flink version paired with the slot total that a generic overview does not carry, then extracts the flink version. modules/recon/kafka-connect-api-exposure.yaml flags an exposed Kafka Connect rest api, keyed on the kafka cluster id paired with the version, then extracts the version. internal/modules/data_pipeline_api_exposure_test.go drives the three modules end to end through ExecuteHTTPModule and asserts the leak alongside the near misses a strict review wants pinned: each service with one keying field missing, a generic health response, a plain 200 and a 404. verify: go test ./internal/modules, each matcher and extractor proven to bite (break -> red, restore -> green).
40 lines
764 B
YAML
40 lines
764 B
YAML
# Apache Airflow API Exposure Detection Module
|
|
|
|
id: airflow-api-exposure
|
|
info:
|
|
name: Apache Airflow API Exposure
|
|
author: sif
|
|
severity: medium
|
|
description: Detects an exposed Apache Airflow webserver through its unauthenticated health endpoint
|
|
tags: [airflow, apache, pipeline, api, exposure, recon]
|
|
|
|
type: http
|
|
|
|
http:
|
|
method: GET
|
|
paths:
|
|
- "{{BaseURL}}/health"
|
|
|
|
matchers:
|
|
- type: status
|
|
status:
|
|
- 200
|
|
|
|
- type: word
|
|
part: body
|
|
words:
|
|
- "\"metadatabase\""
|
|
|
|
- type: word
|
|
part: body
|
|
words:
|
|
- "\"scheduler\""
|
|
|
|
extractors:
|
|
- type: regex
|
|
name: airflow_scheduler_heartbeat
|
|
part: body
|
|
regex:
|
|
- '"latest_scheduler_heartbeat"\s*:\s*"([^"]+)"'
|
|
group: 1
|