minimax

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

• Third-party content exposure detected (high risk: 0.70). The skill's I2V workflow (section "10. Image-to-Video (I2V)" in SKILL.md) accepts a first_frame_image as an arbitrary URL (e.g., "first_frame_image": "https://example.com/image.jpg"), which the API will fetch and incorporate into video generation, meaning untrusted public content can be ingested and materially influence the model's output/behavior.