gemini-imagegen

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Google Search Grounding" feature (example: config with tools=[{"google_search": {}}]) explicitly fetches real-time content from the open web and uses those search results to ground image generation, exposing the agent to untrusted third-party/user-generated content that it will read and interpret.