CVE-2026-41481

Описание

LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters 1.1.2, HTMLHeaderTextSplitter.split_text_from_url() validated the initial URL using validate_safe_url() but then performed the fetch with requests.get() with redirects enabled (the default). Because redirect targets were not revalidated, a URL pointing to an attacker-controlled server could redirect to internal, localhost, or cloud metadata endpoints, bypassing SSRF protections. The response body is parsed and returned as Document objects to the calling application code. Whether this constitutes a data exfiltration path depends on the application: if it exposes Document contents (or derivatives) back to the requester who supplied the URL, sensitive data from internal endpoints could be leaked. Applications that store or process Documents internally without returning raw content to the requester are not directly exposed to data exfiltration through this issue. This vulnerability is fixed in 1.1.2.

A flaw was found in LangChain and langchain-text-splitters. This vulnerability, a Server-Side Request Forgery (SSRF) bypass, allows a remote attacker to redirect a seemingly safe URL to internal network resources. By exploiting unvalidated redirects, an attacker could access sensitive data from internal, localhost, or cloud metadata endpoints. This could result in information disclosure or data exfiltration if the application processes and exposes the content from these redirected requests.