caveman-review
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structural rules and examples for a 'caveman-review' persona. Analysis of the instructions confirms they are limited to formatting and behavioral guidelines for code reviews.
- [SAFE]: No scripts, external dependencies, or binaries are included or referenced in the skill definition.
- [SAFE]: No prompt injection patterns or attempts to bypass safety filters were found. The skill includes standard instructions for switching between styles (e.g., 'stop caveman-review').
Audit Metadata