ai-multimodal
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly supports ingesting public third‑party content (e.g., YouTube URLs and arbitrary public image URIs) as shown in references/video-analysis.md and references/vision-understanding.md via types.Part.from_uri (YouTube URL examples), so the agent will read and interpret untrusted user-generated web content.
Audit Metadata