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 search_grounded_image functionality (SKILL.md and scripts/search_grounded_image.py) explicitly uses Google Search (tools=[{"google_search": {}}]) to ingest real-time web content, which the model reads and uses to ground image generation, exposing it to untrusted third-party pages that could inject instructions.