langgraph

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

• Third-party content exposure detected (high risk: 0.80). The skill includes a search tool ("Search the web for information.") and a ToolNode-based agent loop that accumulates external "sources" (e.g., "source1.com") and returns/reads tool results, so the agent can fetch and ingest untrusted public web content.