design-md

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill fetches external design system files and web pages from user-supplied URLs or the designsmd.vercel.app gallery, which could contain outsider-authored text and prompt injections.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch design systems and tokens at runtime from vercel.com and designsmd.vercel.app, which constitutes an unofficial operational dependency under the dependency gate rules.