nano-banana-2-marketing-image

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

• Third-party content exposure detected (medium risk: 0.30). During the generate and task runtime paths, the CLI ingests outsider-authored free text from the user-supplied --prompt argument and sends it to the model via POST /openapi/v1/chat/text (chat path is present though this skill uses generation/image), which is direct prompt injection exposure.