babysit-pr
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources such as pull request comments, review bot feedback, and CI/CD status messages.
- Ingestion points: The skill reads external feedback from review bots, PR comments, and CI check outputs in
SKILL.md. - Boundary markers: There are no explicit instructions to use boundary markers or to disregard instructions that may be embedded within the PR comments or bot feedback.
- Capability inventory: The skill possesses the capability to execute shell commands via the GitHub CLI (
gh), perform git operations (git fetch,git merge,git push), and post comments back to the PR. - Sanitization: No evidence of sanitization or validation of the external content before processing or acting upon it was found.
Audit Metadata