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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 04:02 AM