save
Warn
Audited by Snyk on Nov 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow extracts content from arbitrary external web pages, YouTube videos, and documents provided via URL or file path by the user, representing active fetching of outsider-authored content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The script uses
uvx --from "markitdown[all]"which dynamically fetches and executes a package from PyPI at runtime without an immutable pin, presenting an unverifiable external dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata