gpt-image-2-product-retouch

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

• Third-party content exposure detected (medium risk: 0.30). In scripts/imagegen.py, the runtime ingests outsider-authored free text directly from the CLI arguments --prompt and optionally --system (messages[*].content) and sends them to the AI Hive POST /openapi/v1/chat/text or POST /openapi/v1/generation/image, without any intermediary selection step.