langchain-fundamentals

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs creating and using a "search" tool that "Search the web for current information" (see the fix-missing-tool-description example and multiple agent examples that include tools=[search] and call web_search(query)), which means the agent will fetch and ingest untrusted public web content that could carry indirect prompt injections.