code-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data in the form of code diffs, pull requests, and implementation plans. This creates a surface for indirect prompt injection if the code under review contains malicious instructions. However, the instructions explicitly restrict the agent to a read-only review mode and do not provide tools for network access, file system modification, or command execution that could be abused.
- [SAFE]: No signs of obfuscation, remote code execution, or unauthorized credential access were detected. The skill instructions prioritize objective failure cases and technical verification, aligning with safe operational practices for AI agents.
Audit Metadata