langchain-rag

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches public web pages via WebBaseLoader/CheerioWebBaseLoader in the "ex-loading-web-pages" example (e.g., loading https://docs.langchain.com) and then uses retrieved documents as model context/agent tool input ("Use this context" in ex-basic-rag-setup and the search_docs agent), meaning untrusted third-party page content is ingested and can influence agent behavior.