audit-skill-conflicts
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a pure meta-documentation tool designed to analyze the coherence of other skills in a collection.
- [SAFE]: The instructions explicitly mandate a read-only approach ('Read-only', 'Present findings. Rewrite nothing until approved').
- [SAFE]: The file enumeration phase (Phase 0) targets standard documentation and configuration paths common in agent platforms (e.g.,
.cursor/rules/*.mdc,skills/*/SKILL.md). - [SAFE]: It contains no executable scripts, shell commands, or network operations.
- [SAFE]: The mention of 'Phase 2 routing dry-run' is explicitly scoped to be skipped if the host environment does not support it, preventing deceptive execution claims.
Audit Metadata