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 git and 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, and gh 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
Risk Level
SAFE
Analyzed
Jul 12, 2026, 05:50 PM
Security Audit — agent-trust-hub — babysitting-pr