wait-what
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns were detected. The skill is composed of natural language instructions intended to guide the AI's communication style.
- [PROMPT_INJECTION]: The instructions steer the AI to adopt a specific technical writing style and use context from a local file. These are standard instructional prompts and do not exhibit characteristics of malicious injection or safety bypass.
- [DATA_EXFILTRATION]: The skill references CONTEXT.md to establish shared terminology. It does not contain tools or commands for network communication or data exfiltration.
Audit Metadata