documentation
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the subprocess module to interact with git and local Python scripts. This includes usage of 'git diff', 'git rev-parse', and 'git log' in 'detect_changes.py' and 'generate_changelog.py', as well as invoking local Python utilities like 'update_catalog.py' in 'sync_docs.py'. The 'SKILL.md' also describes a workflow utilizing 'npx markdownlint-cli' for document formatting.
- [EXTERNAL_DOWNLOADS]: The skill specifies requirements for external packages including 'pyyaml' and 'gitpython' from Python's standard registry, and 'markdownlint-cli' from the Node.js registry, which are necessary for its documented functionality.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it extracts docstrings and comments from the codebase and interpolates them into markdown documentation (e.g., 'SKILL.md' and reports) without sanitization or boundary markers.
- Ingestion points: Python source files processed by 'scripts/update_skill_docs.py' and 'scripts/analyze_code.py'.
- Boundary markers: Absent; extracted docstring content is directly placed into markdown files.
- Capability inventory: The skill can overwrite 'SKILL.md' and other local documentation files, and has access to repository metadata via git commands.
- Sanitization: There is no evidence of escaping or filtering of extracted content before interpolation into documentation.
Audit Metadata