airflow-hitl
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
uvxto execute theafutility from theastro-airflow-mcppackage, which is a resource provided by the authoring organization for Airflow metadata discovery. - [COMMAND_EXECUTION]: Shell commands are used to invoke the
aftool to inspect Airflow configurations, provider versions, and API specifications directly from the environment. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating potentially untrusted data from Airflow XComs and external API inputs into Jinja-templated Markdown bodies.
- Ingestion points: Untrusted data enters the context via
ti.xcom_pullinSKILL.md(Step 4) and throughparams_inputin the external response example (Step 5). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided templates.
- Capability inventory: The skill manages task branching via
HITLBranchOperatorand facilitates network requests to Airflow endpoints using therequestslibrary. - Sanitization: There is no evidence of specific sanitization or escaping of the interpolated data before it is rendered or processed.
Audit Metadata