writing-great-skills

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of documentation, guidelines, and definitions aimed at improving the predictability and structure of other AI agent skills. No suspicious patterns were detected in the text or metadata.
  • [NO_CODE]: There are no scripts, binaries, or automated tool definitions included in this skill. The disable-model-invocation: true configuration in the frontmatter ensures the skill is only invoked manually by a user, preventing autonomous agent behavior.
  • [EXTERNAL_DOWNLOADS]: The ATTRIBUTION.md file mentions a source repository on GitHub (github.com/mattpocock/skills). This is a standard attribution for vendored content and does not involve any automated or hidden network requests during execution.
  • [COMMAND_EXECUTION]: The ATTRIBUTION.md file references a local script ./update-docs for developers to refresh the documentation. This is a common development workflow pattern and is not executed by the agent itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 05:49 PM
Security Audit — agent-trust-hub — writing-great-skills