nano-banana-pro-text-to-image

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path scripts/imagegen.py ingests user-supplied --prompt (and optional --system) and forwards it as prompt/messages to the AI Hive OpenAPI endpoint POST /openapi/v1/chat/text or POST /openapi/v1/generation/image without any intermediate selection or filtering step beyond argument parsing.