nano-banana-pro-poster

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 outsider-provided --prompt free text is sent to the AI Hive runtime via client.generate_image(...) (HTTP POST to /openapi/v1/generation/image), so the workflow directly ingests user-authored text without selecting a specific trusted item.