claude-design-brief
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation hosted on the vendor's domain (cowork.mo.ai.kr) and provides example links to well-known services such as Linear and Stripe. These references are used neutrally as best-practice examples for design projects.
- [PROMPT_INJECTION]: No malicious prompt injection or safety bypass patterns were detected. The skill contains instructional constraints intended to improve output quality and style consistency (e.g., 'AI Slop Avoidance').
- [SAFE]: The workflow relies on user interaction via 'AskUserQuestion' to gather information. The final output is a text-based prompt provided to the user, ensuring a human-in-the-loop process before any further action is taken.
- [SAFE]: References to other skills (e.g., 'moai-design:*') are consistent with the vendor's own ecosystem and represent legitimate cross-skill integration.
Audit Metadata