gpt-image-2-multi-reference-image

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text via the user-supplied --prompt (and optional --system) and forwards it as messages[*].content to POST /openapi/v1/chat/text / POST /openapi/v1/generation/image, so an outsider can submit arbitrary poison text at submission time.