audit-skills

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a read-only auditing tool. It is designed to read existing documentation and skill files (skills/*/SKILL.md, specs/skill-audit/spec.md, AGENTS.md) and generate a single markdown report in a .plans/ directory.
  • [SAFE]: No network operations, external downloads, or remote code execution patterns were detected.
  • [SAFE]: The skill explicitly includes constraints preventing the modification of source skill files, maintaining a read-only posture for the target directories.
  • [SAFE]: Tool usage is restricted to standard filesystem operations (read, glob, and writing to a specific report path) and an optional internal MCP for knowledge base lookups.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:04 PM
Security Audit — agent-trust-hub — audit-skills