review-and-ship
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, specifically git diffs, pull request descriptions, and comments. This constitutes an attack surface where an attacker could embed malicious instructions in code comments or PR metadata to influence the agent's behavior during the review process.
- [SAFE]: Aside from the inherent risk of processing untrusted code, the skill follows security best practices. It does not contain hardcoded credentials, obfuscated code, persistence mechanisms, or unauthorized network operations. Tools used (git, gh, npm) are restricted to standard development tasks.
Audit Metadata