project-docs
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository (e.g., existing documentation, file structure, and Git history) to generate new documentation, such as AGENTS.md, which could potentially contain instructions for AI agents.
- Ingestion points: Reads README.md, AGENTS.md, docs/ directory, file structure, and Git history.
- Boundary markers: The skill explicitly requires a two-step process where it must wait for user confirmation after an audit phase before modifying or creating any files.
- Capability inventory: The skill uses file read and write operations on the local filesystem but has no network or shell execution capabilities.
- Sanitization: The skill uses strict templates and relies on manual human review to validate content before persistence.
Audit Metadata