skills/astronomer/agents/airflow-hitl/Gen Agent Trust Hub

airflow-hitl

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data via Jinja templates in the body parameter of HITL operators, creating a potential surface for indirect injection if data pulled from previous tasks contains malicious instructions.\n
  • Ingestion points: Untrusted data enters the agent context via XCom pulls (e.g., ti.xcom_pull) used in the body and subject parameters of HITL operators in SKILL.md.\n
  • Boundary markers: The instructions do not specify the use of delimiters or provide explicit warnings to the agent to ignore instructions embedded in the interpolated data.\n
  • Capability inventory: The skill demonstrates network operations via the requests library and system command execution via the af CLI tool.\n
  • Sanitization: No evidence of content sanitization, escaping, or validation is provided for the interpolated data.\n- [COMMAND_EXECUTION]: The skill provides instructions to execute the af CLI tool to perform environment-specific discovery tasks, including fetching registry signatures, querying configuration details, and checking installed provider versions. These are used to adapt code to the specific Airflow environment.\n- [EXTERNAL_DOWNLOADS]: The skill references standard and expected packages from the official Apache Airflow ecosystem, specifically apache-airflow-providers-standard.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:34 PM
Security Audit — agent-trust-hub — airflow-hitl