babysitting-pr
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard development tools, including
gitand the GitHub CLI (gh), to manage source code and pull request states. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of processing external, untrusted data.
- Ingestion points: It retrieves data from pull request comments, review threads, and GitHub Action logs via commands like
gh pr view,gh api, andgh run view --log-failed(found in sections 2 and 3). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from interpreting instructions embedded within the PR comments or log outputs as authoritative commands.
- Capability inventory: The skill has significant capabilities, including modifying code, committing changes, and pushing to remote branches (
git push), as well as triggering workflow re-runs (gh run rerun). - Sanitization: The skill does not implement any validation or sanitization of the text retrieved from the GitHub API before analyzing it for "actionable feedback."
Audit Metadata