gpt-image-2-image-edit

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text enters at runtime via the CLI --prompt (and optional --system) which is sent to the AI Hive endpoint as prompt/messages in cmd_image → AiHiveClient.generate_image (/openapi/v1/generation/image).