commit-documentor
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes commit diffs to determine if documentation updates are required. Since commit messages and code comments are untrusted inputs, they could contain instructions designed to trick the agent into omitting changes, including sensitive data in documentation, or misinterpreting the code's impact.
- Ingestion points: Commit logs and diffs are accessed via
git log,git diff, andgit show(SKILL.md, Step 2). - Boundary markers: No explicit markers or delimiters are used to separate the untrusted commit content from the agent's own instructions.
- Capability inventory: The skill possesses file system access, performs git operations (commit, push), and creates pull requests via the
ghCLI tool (scripts/doc-repo.sh). - Sanitization: The skill does not perform sanitization on commit content, relying instead on the requirement for explicit user approval of the final documentation diff as a primary security control.
Audit Metadata