provider-integration-templates

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

• Third-party content exposure detected (high risk: 0.90). The skill includes examples that load and consume arbitrary web content and external API responses—e.g., the LangChain RAG example uses WebBaseLoader to fetch web pages (examples/langchain-rag-example.md) and the Vercel tools example provides a makeApiRequest tool that fetches arbitrary URLs (examples/vercel-tools-example.md)—so the agent is expected to read untrusted third-party content as part of its workflow.