nano-banana

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

• Third-party content exposure detected (high risk: 0.90). The skill's references/guide.md explicitly documents "Google Search Grounding" and shows using tools=[{"google_search": {}}] so the agent will fetch and consume real-time public web/search results (untrusted third-party content) that can influence generation and subsequent actions.