TikTok Ad Creative Generation

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

• Third-party content exposure detected (high risk: 0.70). The skill's "Using Reference Images" section and examples explicitly accept arbitrary image_urls (e.g., "image_urls": ["https://example.com/product-image.jpg"]) which the each::sense API will ingest to guide generation, meaning untrusted third‑party content can be read/interpreted and materially influence generation behavior.