simplify-docs
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (code comments and markdown files) which could be manipulated to influence agent behavior during the review and fixing process.
- Ingestion points: Files identified in the scope (via
git diff,gh pr view, or directory sweeps) are read by the review agents as described in SKILL.md. - Boundary markers: No explicit delimiters or instructions are used to distinguish between the data being reviewed and the instructions for the agent.
- Capability inventory: The skill utilizes
git,gh(GitHub CLI), and performs file system read/write operations to apply fixes across the working directory. - Sanitization: No sanitization, escaping, or validation is performed on the content of the files before they are processed by the review agents.
Audit Metadata