nanobanana-mcp-image-generation

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly documents an enable_grounding option (e.g., generate_image(..., enable_grounding=True)) that uses "Google Search grounding", which indicates the service fetches and ingests public web search results to influence image generation and thus exposes the agent to untrusted third‑party content.