jb-docs-scraper

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

• Third-party content exposure detected (high risk: 0.90). references/scrape_docs.py directly uses crawl4ai's AsyncWebCrawler to crawl and convert a user-supplied base URL (see SKILL.md examples like https://mediasoup.org/...) into local markdown files in ./docs, thereby fetching and ingesting arbitrary public website content.