cloudflare-images

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly ingests and processes arbitrary external/user-provided images (e.g., "Method 2: Upload via URL" — "Ingest images from external sources" and the Workers examples that call fetch(imageURL, ...) such as "https://example.com/image.jpg", plus Direct Creator Upload for user uploads), so it clearly consumes untrusted third‑party content as part of its workflow.