langchain-fundamentals

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

• Third-party content exposure detected (high risk: 1.00). The skill's documentation and examples explicitly instruct agents to include a "search" tool that "Search the web for current information" and returns web_search(query) (see the "fix-missing-tool-description" example and multiple create_agent examples using tools=[search] in SKILL.md), which means the agent will fetch and read open/public third-party web content that can influence its actions.