markitdown

Warn

Audited by Snyk on Mar 14, 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 accepts and downloads arbitrary web URLs and HTML for conversion (see "Convert Web URL (via download)" in examples.md and the convert() doc in reference.md), so the agent ingests untrusted public web content that could influence downstream processing.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 03:25 PM
Issues
1