extract-design-system

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and references/workflow.md explicitly instruct the agent to fetch and analyze a user-supplied public website URL via "npx extract-design-system " and to read the resulting .extract-design-system/normalized.json, which is untrusted third-party content that can directly influence generated token files and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs running external CLI packages at runtime—specifically "npx extract-design-system " (which fetches and executes the extract-design-system npm package from the registry) and also "npx playwright install chromium"—so remote code is downloaded and executed as a required part of the workflow.