ai-multimodal
Warn
Audited by Snyk on Apr 11, 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 skill explicitly ingests public, untrusted web content — e.g., SKILL.md and references/video-analysis.md show YouTube URL support and references/vision-understanding.md shows types.Part.from_uri for public image URLs — meaning the agent fetches and analyzes arbitrary third-party pages/videos which could contain instructions that influence model outputs or downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata