langgraph

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly defines and uses a web "search" tool ("Search the web for information.") and a ToolNode/ResearchState that accumulates external "sources" (e.g., "source1.com") which the agent reads and uses in downstream nodes, so untrusted public web content can be fetched and materially influence agent decisions.