image-ad-clone
Warn
Audited by Snyk on Aug 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In
skills/image-ad-clone/scripts/validate_image.py, the validator ingests the caller-provided--prompt(and optionally uses caller-provided reference images via--image-ref/--source-asset-id) and forwards that free-text intobuild_prompt(...)and then into the runtime API request body as{"prompt": prompt}, so outsider text can directly reach the LLM at generation time without any prior selection step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata