fix-my-look

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

• Third-party content exposure detected (high risk: 0.85). High: the required workflow ingests outsider free text via <change_prompt> (user-provided, i.e., not authored by the operating user/organization in the sense required) into multiple LLM prompt contexts for generate_image_edit and generate_reference_video (Step 2/4), which can enable indirect prompt injection through attacker-written instructions.