generate-docs

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands defined in the project's documentation map configuration, specifically build and map commands. It also utilizes standard development tools such as git for diffing, npx astro for build verification, and structural analysis tools like dependency-cruiser and madge.
  • [EXTERNAL_DOWNLOADS]: The skill instructions reference the author's public repository (gtrabanco/agentic-workflow) for installation and alternative branch usage, which matches the provided author metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of project source code and git diffs to generate documentation. While this is an attack surface, the instructions include constraints to use deterministic tool outputs for structural maps and require factual citations for all generated content, mitigating the risk of following instructions embedded in source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 10:34 PM
Security Audit — agent-trust-hub — generate-docs