convert-to-markdown

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow directly fetches and ingests arbitrary public web content and user-generated media (e.g., scripts/html-to-md.py sends arbitrary URLs to a Crawl4AI server, scripts/mhtml-to-md.py can load HTTP(S) MHTML pages, and scripts/youtube-transcript.py downloads YouTube metadata and captions), so untrusted third‑party content is read and could influence downstream agent behavior.