fal-ai

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

• Third-party content exposure detected (high risk: 0.90). The skill's examples explicitly accept and ingest arbitrary external image URLs (e.g., image_url, mask_url, control_image_url, base_image_url, swap_image_url in the Image-to-Image, Inpainting, ControlNet, Background Removal, and Face Swap sections), which are untrusted third-party content that the model reads/uses at runtime and can materially influence generation behavior.