review-sslb
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the AI agent and does not contain any executable scripts, binary files, or network operations.
- [SAFE]: The instructions include a 'Jinyiwei' role (Independent Oversight) which explicitly directs the agent to check for omissions, misjudgments, and process violations, serving as a self-correction mechanism to improve the accuracy of the review.
- [SAFE]: The skill includes a dedicated 'Ministry of War' (兵部) role focused on security review, specifically instructing the agent to look for injection risks, input validation issues, sensitive information exposure, and permission controls in the code being reviewed.
- [SAFE]: No obfuscation, data exfiltration patterns, or attempts to bypass system safety filters were identified in the instructions.
Audit Metadata