eachlabs-product-visuals

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill accepts and ingests arbitrary external image URLs (e.g., the "image_urls"/"image_url"/"ref_image_url" fields shown in the "Product on White Background", "Lifestyle Scene Generation", "Product Video from Image" workflows and Bria model parameters), so the service will fetch untrusted third-party content that the agent must read/interpret.