CVE-2026-41481

描述

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.

如何修補 CVE-2026-41481

要修補 CVE-2026-41481,請將受影響套件升級到下列已修補版本。

• —升級至 1.1.2 或更新版本
• —升級至 1.1.2 或更新版本

CVE-2026-41481 正在被利用嗎?

低 — EPSS 為 0.0%,目前沒有觀察到大規模利用活動。

受影響套件(2)

• from 0, < 1.1.2
• from 0, < 1.1.2

CVSS 分數

參考連結(4)

• ADVISORYnvd.nist.gov/vuln/detail/CVE-2026-41481
• PATCHgithub.com/langchain-ai/langchain
• WEBgithub.com/langchain-ai/langchain/security/advisories/GHSA-fv5p-p927-qmxr
• WEBgithub.com/pypa/advisory-database/tree/main/vulns/langchain-text-splitters/PYSEC-2026-77.yaml