building-ai-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly documents and requires internet-facing tools such as google_search and load_web_page (see references/ADK-AGENT-AND-TOOLS.md and INSTRUCTIONS.md) that fetch and ingest public web pages/URLs for the agent to read, summarize, and act on, so untrusted third-party content can directly influence tool calls and decisions.