review-pr
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for manual or automated code review and does not perform any automated actions, network requests, or command executions.
- [NO_CODE]: No executable scripts or binary files are included in the skill; it consists entirely of markdown documentation and configuration metadata.
- [PROMPT_INJECTION]: The skill is intended to review pull request data, which constitutes processing untrusted external input.
- Ingestion points: Pull request content (code and diffs) enters the agent context.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined in SKILL.md.
- Capability inventory: The skill does not define or use any tools, scripts, or subprocesses.
- Sanitization: No sanitization or validation of the processed code is performed.
Audit Metadata