langchain-core-workflow-b

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

• Third-party content exposure detected (high risk: 0.80). The skill defines web-search tools that are intended to fetch and return open/public web content (the search_web tool in "Step 1" and the async_search example using aiohttp in "Advanced Patterns"), so the agent would ingest untrusted third‑party web results that could influence its subsequent actions.