nano-banana-pro-image-edit

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow only ingests outsider-authored free text from the caller-provided --prompt (and optional --system) arguments and sends them to the AI Hive API via chat_text/generate_image, without any automatic ingestion of third-party feeds/queues.