github-pr-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from GitHub pull requests, creating a surface for indirect prompt injection. Malicious instructions within a PR diff or description could attempt to influence agent behavior.
- Ingestion points: Pull request descriptions and code diffs accessed via gh pr view and gh pr diff in SKILL.md.
- Boundary markers: Instructions do not include markers or warnings to separate PR content from agent instructions.
- Capability inventory: The skill executes gh pr checkout, gh pr view, and gh pr diff.
- Sanitization: PR content is processed without filtering or sanitization.
- [COMMAND_EXECUTION]: The skill relies on executing the GitHub CLI (gh) to interact with repositories. While this is the intended functionality, it involves local environment modification via gh pr checkout.
Audit Metadata