reviewing-wireframes
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected across the analyzed files. The skill provides instructions for document review without any dangerous capabilities.
- [PROMPT_INJECTION]: Analysis of instructions found no evidence of safety filter bypasses, role-play jailbreaks, or system prompt extraction attempts. The directive to emit a specific verdict string is part of the skill's core logic and does not constitute a malicious override.
- [DATA_EXFILTRATION]: The skill does not contain any code or instructions for network communication or accessing sensitive local files such as credentials or SSH keys.
- [REMOTE_CODE_EXECUTION]: No external script downloads or package installations are performed. The skill does not use dynamic execution functions or subprocess calls.
Audit Metadata