create-video

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and model docs explicitly instruct fetching and ingesting arbitrary public image/video/audio URLs (e.g., SKILL.md and model refs: "pass image_url" for I2V, Sora 2 Pro's "From a video URL" character extraction, and many references noting image_urls/audio_url), which the agent will read/interpret to condition generation and drive subsequent model actions—meeting the criteria for untrusted third‑party content that could carry indirect prompt injections.