image-gen
Warn
Audited by Snyk on Apr 9, 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's Interaction Flow Step 4 ("Reference Images" URL mode) explicitly accepts arbitrary external image URLs and builds fileData objects with fileUri to include in the generation request, so untrusted third-party content from public URLs will be ingested and can influence the image-generation behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata