markitdown-skill
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: 1.00). The skill explicitly ingests open web content — e.g., converting YouTube URLs, HTML pages, RSS/Atom feeds, and Wikipedia pages (see examples using markitdown "https://www.youtube.com/..." and md.convert("https://en.wikipedia.org/...")), so the agent reads untrusted, user-generated third‑party content as part of its workflow.
Audit Metadata