code-reviewer
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or executable code detected in the skill instructions. The content consists entirely of text-based guidelines for a code review persona.
- [DATA_EXFILTRATION]: No sensitive data access, credential harvesting, or unauthorized network transmission patterns were identified.
- [PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety constraints or override the agent's core instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code, which is a known surface for indirect prompt injection. 1. Ingestion points: Code provided for review in SKILL.md. 2. Boundary markers: None explicitly defined. 3. Capability inventory: The persona is instructed to use static analysis and security scanning tools. 4. Sanitization: No explicit sanitization or escaping of input code is mentioned.
Audit Metadata