git-fix-pr

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard development tools, specifically git and the GitHub CLI (gh), to manage repository state and Pull Request interactions. These commands are restricted to the local environment and the project's GitHub repository.
  • [PROMPT_INJECTION]: The skill processes external data from Pull Request comments and descriptions via gh pr view and gh api calls. This represents a surface for indirect prompt injection where malicious instructions could be embedded in PR content. However, the risk is mitigated by a mandatory human-in-the-loop planning phase where the user must approve specific actions based on the triaged blockers before implementation.
  • Ingestion points: GitHub API responses (comments, reviews, PR body) retrieved via the gh tool in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters for external content in its instructions.
  • Capability inventory: The skill can perform git commit, git push, and gh CLI commands to post replies or update PR text as described in SKILL.md.
  • Sanitization: No explicit sanitization or filtering of retrieved PR content is specified in the implementation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 11:45 AM
Security Audit — agent-trust-hub — git-fix-pr