google-gemini-api

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly enables "Grounding with Google Search" (see the Grounding/groundingMetadata and webPages sections) where the agent automatically performs web searches and ingests public web pages/URLs and their snippets into responses, thus exposing it to untrusted third‑party content that could carry indirect prompt injections.