nano-banana-2

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly includes a "With Google Search Grounding" example and an Input Option enable_google_search that enables real-time Google Search grounding, and it accepts arbitrary image URLs for edits, meaning the agent will fetch and read open/public web content that can influence its generation workflow.