markitdown

Warn

Audited by Snyk on Mar 3, 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 public, user-generated web content (e.g., YouTube transcriptions via examples like md.convert("https://www.youtube.com/watch?v=VIDEO_ID") and HTML/web page conversion in SKILL.md), so it ingests untrusted third-party content that the tool reads and returns as text used in workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 08:48 PM