code-review-excellence
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides educational content and best practices for code reviews, focusing on knowledge sharing and code quality.
- [PROMPT_INJECTION]: The skill's intended use involves processing untrusted data from Pull Requests, identifying a surface for indirect prompt injection. 1. Ingestion points: The process involves reading PR descriptions, linked issues, and code changes as specified in Phase 1 and Phase 3 of SKILL.md. 2. Boundary markers: No explicit instructions for the use of delimiters or ignore commands for the untrusted data. 3. Capability inventory: References a helper script 'scripts/pr-analyzer.py' for PR analysis. 4. Sanitization: No mentioned sanitization or filtering of external content before processing.
Audit Metadata