Art

Warn

Audited by Snyk on Mar 5, 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). The Ad-hoc YouTube Thumbnail workflow explicitly lists "URL (fetch and analyze)" as an input type and requires extracting TITLE and SUBTITLE from that fetched content (Workflows/AdHocYouTubeThumbnail.md Step 1), meaning the agent will read and act on untrusted public web/user-provided pages to drive image-generation prompts and follow-up actions, which can enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:38 AM