extract-design-system

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

• Third-party content exposure detected (high risk: 0.85). The skill’s purpose is to “reverse-engineer a design system from any publicly accessible website,” which implies it fetches and scrapes outsider-authored public web page content at runtime and feeds the extracted text/CSS into the agent’s LLM context for analysis.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's install step invokes "npx skills add arvindrk/extract-design-system", which at runtime fetches and executes the external package (upstream: https://github.com/arvindrk/extract-design-system), so remote code would be pulled and run as a required dependency.