building-adk-agents

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly includes internet-access tools (e.g., google_search and load_web_page) and shows workflows that fetch and have the agent read/interpret arbitrary public URLs (see "Pre-built Tools → Internet Access Tools" and the web_scraper/SequentialAgent examples), which exposes the agent to untrusted third‑party content that can influence its tool use and decisions.