code-review
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and provides templates and checklists for code review processes. It does not include executable scripts, network operations, or sensitive file access.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it is designed to analyze untrusted external code (e.g., pull request diffs). Ingestion points: Code changes and pull request data (referenced in SKILL.md). Boundary markers: Absent. Capability inventory: No tool-calling or execution capabilities are defined within the skill. Sanitization: No explicit validation or filtering of external content is specified. This is an inherent structural risk for code review tools rather than an intentional malicious pattern.
Audit Metadata