markitdown

Warn

Audited by Snyk on Feb 21, 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 converts open web content such as HTML pages and YouTube URLs (see SKILL.md, references/file_formats.md, and examples like convert("https://www.youtube.com/...")), and several scripts (e.g., scripts/convert_with_ai.py) feed that untrusted, user-provided content into LLMs for interpretation and AI-enhanced descriptions—meaning third-party content is ingested and can materially influence the tool's outputs and downstream behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 04:21 AM