extract-design-system

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

• Third-party content exposure detected (high risk: 0.85). Yes: the required runtime workflow ingests outsider-authored free text from the user-supplied live URL via Firecrawl page discovery/scraping and/or Playwright link discovery, which then drives in-page extraction that captures element text (e.g., textContent/innerText) into JSON that is later composed into LLM prompts for Claude curation/distillation.