w-review-plan

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for the agent to perform plan reviews (Goals, Assumptions, Tasks, Risks, and References).
  • [SAFE]: The instructions explicitly prohibit the creation of files, branches, or scaffolds, restricting the agent to 'Chat only' mode.
  • [SAFE]: The frontmatter configuration disable-model-invocation: true provides a platform-level restriction that prevents the skill from invoking other tools or models.
  • [SAFE]: The skill actually encourages security best practices by instructing the agent to 'Flag missing deferrals for product scope, secrets, or destructive ops.'
  • [SAFE]: No network activity, obfuscation, sensitive file access, or remote code execution patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 12:07 AM
Security Audit — agent-trust-hub — w-review-plan