refactor-rules
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as an advisory tool, performing diagnostic analysis and reporting violations without executing untrusted code or making unauthorized system changes.
- [SAFE]: Although the skill ingests project source code to infer rules, the use of high dominance thresholds (e.g., 90% conformance) and mandatory human-in-the-loop confirmation effectively mitigates the risk of indirect prompt injection from codebase content.
- [SAFE]: Technical analysis of the provided Node.js scripts confirms they are local, zero-dependency utilities without network capabilities, credential access, or obfuscated logic.
- [SAFE]: The skill maintains clear boundaries between analysis (read-only) and enforcement (advisory), ensuring that all architectural decisions remain under human control.
Audit Metadata