massgen-release-documenter
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute various CLI tools and local scripts to automate documentation tasks.
- Evidence: The instructions include commands for
git(tag, push, mv, rm),gh(GitHub CLI),make(building Sphinx docs), anduv(running local Python scripts likescripts/sync_readme_pypi.py). - Risk: The agent is empowered to modify repository state and push changes, requiring human oversight of the resulting commits and tags.
- [INDIRECT_PROMPT_INJECTION]: The skill involves a workflow where the agent ingests data from external sources to generate documentation, which could contain malicious content.
- Ingestion points: Git commit history (
git log) and GitHub Pull Request metadata (gh pr list). - Boundary markers: None. The skill lacks instructions for the agent to differentiate between legitimate change descriptions and potentially malicious instructions embedded within commit/PR text.
- Capability inventory: The agent can perform file writes, script execution, and git push operations across the project.
- Sanitization: The skill does not prescribe any sanitization or validation of the ingested commit or PR text before processing it into the CHANGELOG.
Audit Metadata