google-gemini-api

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly performs real-time Google Search grounding (see "Grounding with Google Search" and examples using tools: [{ googleSearch: {} }] and groundingMetadata.webPages) so the agent fetches and ingests open web pages/snippets (untrusted third‑party content) and incorporates them into responses, exposing it to indirect prompt injection.