code-quality-review
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured workflow for evaluating code quality, verifying bug fixes, and reviewing feedback. It emphasizes evidence-based reasoning, requiring
file:linecitations for all findings. - [SAFE]: Instructions include specific phases for risk detection, targeting dependency upgrades, migrations, API changes, and security-sensitive modifications.
- [SAFE]: The skill utilizes local scripts (e.g.,
.claude/scripts/code_graph,node .claude/scripts/ai-signal-scan.cjs) for analysis. These are internal project tools and do not involve remote code execution from untrusted sources. - [SAFE]: Data handling is restricted to creating local report files in
tmp/reports/for persistence across review sessions. No suspicious network operations or credential harvesting patterns were found. - [SAFE]: Indirect prompt injection risks are mitigated by a skeptical 'Review Mindset' that requires tracing logic paths and verifying claims against the actual codebase rather than taking instructions at face value.
Audit Metadata