generate-mixed-media
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly loads and composes images from external URLs (see Step 4 "Loading source image at platform dimensions" and the selectedImage.image_url fields / example URLs like https://ik.imagekit.io/example/...), and also ingests adCopy provided with the request, so it fetches and interprets untrusted third-party content.
Audit Metadata