sec-policy
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project files to generate security documentation, creating a vulnerability surface for embedded instructions.
- Ingestion points: The skill reads existing SECURITY.md, README, build files, and code structure from the repository.
- Boundary markers: There are no instructions to wrap ingested content in delimiters or to disregard embedded instructions.
- Capability inventory: The skill can write files to the local scan directory or directly to the repository upon user command.
- Sanitization: The instructions do not specify any validation or sanitization steps for the external content before it is processed by the agent.
Audit Metadata