gpt-image-2

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

• Third-party content exposure detected (medium risk: 0.30). The skill runtime workflow ingests user-supplied free text via the prompt field in the synchronous image generation/editing POST requests (e.g., .../openai/images/edits uses -F "prompt=..."), which is then consumed by the model alongside provided images.