openrouter
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: 0.70). The skill includes Vision Model examples that ingest and interpret arbitrary image URLs provided by users (see "Vision Models" -> analyzeImage(imageUrl: string, question: string and "Multi-Image Analysis"), which means the agent will read/interpret untrusted third‑party content from public URLs.
Audit Metadata