extract-design-system

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

• Third-party content exposure detected (low risk: 0.10). The workflow extracts design tokens from arbitrary public websites via a headless Chromium crawl, which is an active search/fetch of outsider-authored content.

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 dynamically fetch and install an unverified third-party GitHub repository (arvindrk/extract-design-system) at runtime via npx skills add, presenting a medium-tier unofficial operational dependency.