langgraph

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly shows nodes invoking search_web(query) and a LangChain DuckDuckGoSearchRun tool (agent_with_tools) to fetch open-web results that the agents read and incorporate into prompts and routing decisions, so untrusted third‑party content can materially influence tool use and next actions.