nano-banana-pro

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow executes scripts/generate_image.py, which ingests outsider-provided free text from the --prompt argument (e.g., user-supplied “your image description” or “edit instructions”) directly into client.models.generate_content(..., contents=...).