code-reviewer

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code, commands, or data exfiltration patterns were found. The skill references standard industry tools and best practices for code quality and security.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code, which creates a surface for indirect prompt injection. 1. Ingestion points: User-provided code and files for review. 2. Boundary markers: No explicit delimiters are specified. 3. Capability inventory: Mentions CLI, CI/CD, and IDE integrations. 4. Sanitization: No sanitization methods are defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:05 PM
Security Audit — agent-trust-hub — code-reviewer