openrouter
Warn
Audited by Snyk on Apr 25, 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). SKILL.md explicitly includes Vision examples (analyzeImage and compareImages) that accept arbitrary image URLs and pass those third‑party resources to the model for analysis, so untrusted external content would be ingested and could influence model outputs and subsequent tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata