markitdown

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly lists ingesting HTML and "YouTube URLs" (public, user-generated web content) in Supported Formats and also allows third‑party plugins (--use-plugins), so the agent would read untrusted web content as part of its conversion workflow and that content could influence downstream LLM actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 12:16 AM