doc-maintenance
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted commit messages from git history to generate documentation updates.
- Ingestion points: Commit logs retrieved via
git log. - Boundary markers: None; the skill does not use specific delimiters to separate commit content from instructions.
- Capability inventory: Branch creation, file modification, and PR creation via
gh. - Sanitization: Commit messages are summarized directly into the PR body without escaping.
- [COMMAND_EXECUTION]: Uses standard
gitandghCLI tools to analyze history and manage Pull Requests. These operations are consistent with the skill's stated purpose. - [DATA_EXFILTRATION]: Performs network communication with GitHub to create pull requests as part of its documented workflow.
Audit Metadata