code-review-pro
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): This skill handles external untrusted code which could contain malicious instructions. 1. Ingestion points: User-provided code snippets. 2. Boundary markers: Absent. 3. Capability inventory: Limited to text-based analysis; no file or network access defined. 4. Sanitization: No specific filtering or validation steps.
Audit Metadata