code-review-and-quality
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional markdown files that define a code review process. It does not contain any executable scripts, shell commands, or network operations.- [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted data (code diffs and PR descriptions), it includes robust defensive instructions to treat such content strictly as data and to ignore any embedded commands or social engineering attempts. This aligns with the skill's primary purpose and follows security best practices for agentic code review. Ingestion points: SKILL.md (diffs, PR descriptions, comments, source code). Boundary markers: Present in 'Security and Trust Boundaries' section. Capability inventory: No execution, modification, or merging capabilities. Sanitization: Defensive instructions provided to the agent.
Audit Metadata