review
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's use of git and file system access is limited to read-only operations for the purpose of code review.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted source code from git diffs and files. 1. Ingestion points: Git diff outputs and file contents (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: git diff and file read access. 4. Sanitization: Absent.
Audit Metadata