langchain-agent-builder

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

• Third-party content exposure detected (high risk: 0.90). This skill's examples and tool integrations explicitly include a "search" Tool (e.g., the create_react_agent example with Tool(name="search", func=search_function, description="搜索网络信息")) and lists public search providers (Google Search, DuckDuckGo) under "工具集成", so the agent is expected to fetch and ingest untrusted public web content at runtime.