fashion-model-photography

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests external product images via a product_image URL (see Tool Definition and the integration pattern where analyzeProduct(params.productImage) and imageGenTool images: [{ url: params.productImage }] are called), meaning it fetches and interprets arbitrary third-party content supplied by users or public URLs.