NYC

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
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:38 PM