tracing-downstream-lineage
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data by reading Airflow DAG source code to identify dependencies. This creates a potential surface for indirect prompt injection if the source code contains malicious instructions.
- Ingestion points: DAG source code retrieved via the get_dag_source_code tool (SKILL.md).
- Boundary markers: The skill does not provide specific instructions to delimit or ignore instructions within the processed source code.
- Capability inventory: Utilizes tools for listing DAGs and reading source code.
- Sanitization: No explicit sanitization or filtering of the code content is described before analysis.
Audit Metadata