markitdown
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests untrusted, user-generated web content — for example it converts YouTube URLs and fetches web pages (see md.convert("https://www.youtube.com/watch?v=VIDEO_ID") and HTML/web-page conversion entries and examples), so the agent will read and process arbitrary third‑party content.
Audit Metadata