sora

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly accepts arbitrary public image URLs for image-guided generation (see SKILL.md "If the request is image-guided, use an image_url reference" and scripts/sora_video_generate.py which puts payload["image_reference"] = {"image_url": args.image_url}), meaning untrusted third-party content is ingested and can influence the model's outputs and subsequent actions.