code-review
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on improving the quality of code reviews through evidence-based claims and verification gates.
- [COMMAND_EXECUTION]: The skill instructs the agent to run standard development verification tools such as 'npm', 'pnpm', 'pytest', and 'cargo'. These are legitimate uses within the scope of a developer-oriented skill and do not involve unauthorized network operations or privilege escalation.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external feedback. It mitigates injection risks by requiring technical verification and critical evaluation of all external suggestions before implementation.
- Ingestion points: External code review feedback (referenced in SKILL.md and receiving-feedback.md).
- Boundary markers: None specified.
- Capability inventory: Local shell commands for code quality checks (npm, pnpm, pytest, cargo, ruff, grep).
- Sanitization: The protocol mandates rigorous technical verification and pushes back on incorrect logic, serving as a functional defense against malicious suggestions.
Audit Metadata