babysit
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes pull request metadata and review threads which may contain instructions from external contributors.
- Ingestion points: Fetches PR state and review content via
gh pr viewandgh pr checks. - Boundary markers: None; external content is not explicitly delimited.
- Capability inventory: The agent has the ability to commit code, push to the repository, and manage CI runs via the GitHub CLI.
- Sanitization: External data is processed without sanitization or validation.
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with Git and the GitHub CLI to automate the pull request lifecycle.
Audit Metadata