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 SKILL.md explicitly shows a "Google Search Grounding (Real-time Data)" example that adds a "google_search" tool to fetch current web search results (public, untrusted third-party content) which the agent is expected to use to inform image generation, so those external results could influence subsequent actions.