peer-review
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates technical peer reviews by analyzing project artifacts and proposing refinements.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing untrusted project data (plans, requirements) and having the ability to modify local files.
- Ingestion points: Step 1 reads various local files including package.json, requirements.txt, and PR descriptions.
- Boundary markers: There are no explicit instructions for the agent to ignore instructions embedded within the files it reviews.
- Capability inventory: The agent can write to files to update implementation plans (Step 4).
- Sanitization: The skill does not perform sanitization on the external content it processes.
Audit Metadata