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: 0.90). This skill explicitly ingests public web content (it supports converting HTML/web pages and fetching YouTube video transcriptions) which are untrusted/user-generated sources that the agent reads and processes as part of its conversion workflow, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 04:01 AM