nano-banana-product-retouch

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text provided via the required --prompt argument is packaged into the runtime request body (messages[].content / prompt) and sent to the AI Hive openapi/v1/chat/text or openapi/v1/generation/image endpoints, making it directly ingestible by the AI agent workflow.