image-to-motion

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow for image-to-motion ingests the user-provided start image and requires “Every legible string, transcribed verbatim” (from that image) which is then embedded into the outbound generation prompt, meaning outsider-authored free text from the image can be LLM-readable and influence generation.