code-review
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a multi-agent review process where two sub-agents compete to find issues in code changes. This is a common and safe prompting technique used to improve the quality and depth of AI-generated analysis.- [SAFE]: The skill processes code changes from git diffs, which constitutes an indirect prompt injection surface area (Category 8). However, this ingestion is necessary for the skill's primary function of code review and no malicious exploitation patterns were observed.
- Ingestion points: Git diff outputs and branch comparison data.
- Boundary markers: Absent; the skill does not explicitly instruct sub-agents to ignore instructions embedded within the code being reviewed.
- Capability inventory: Static analysis of code architecture and implementation details.
- Sanitization: Not applicable as the skill performs read-only analysis.
Audit Metadata