vision-multimodal
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow ingests user-provided image/PDF content (including via an arbitrary URL for images) by sending base64-encoded image/document data plus free-text instructions directly to the Claude API.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata