code-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The content consists entirely of instructional documentation for human or AI code reviewers. It focuses on identifying runtime errors, performance issues, and security vulnerabilities in code. No executable scripts, network requests, or sensitive data access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: As a code review skill, it is designed to ingest and analyze external, untrusted code. This represents a potential attack surface where malicious instructions could be embedded within the source code or comments being reviewed to influence the agent's output. This is a characteristic of the skill's primary function rather than a malicious implementation.
Audit Metadata