nano-banana-2-poster

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

• Third-party content exposure detected (low risk: 0.10). [scripts/imagegen.py at runtime ingests outsider-provided free text only from the CLI argument --prompt (and optional --system) into client.generate_image() → HTTP POST /openapi/v1/generation/image as the prompt field; there is no evidence it reads any outsider-authored feed/inbox/ticket/queue content automatically.]