doc-writer

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • External Data Processing: The skill is designed to research features by reading content from GitHub issues and pull requests. While the ingestion of untrusted external data represents a surface for indirect prompt injection, the skill incorporates a 'Research and Propose' phase that requires explicit user approval of a plan before any file modifications are made.
  • Official Tool Integration: It utilizes the gh CLI to interact with official project repositories. These operations are limited to research and are appropriate for the skill's stated purpose of documenting software features within the vendor's ecosystem.
  • Access Controls and Guardrails: The skill instructions strictly limit file modifications to the docs/ directory and include specific prohibitions against editing generated files such as enterprise/policies.md, which helps maintain the integrity of the project's core configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 02:47 PM
Security Audit — agent-trust-hub — doc-writer