CVE-2026-26019: LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/community is a web crawler...

Description

LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/community is a web crawler that recursively follows links from a starting URL. Its preventOutside option (enabled by default) is intended to restrict crawling to the same site as the base URL. The implementation used String.startsWith() to compare URLs, which does not perform semantic URL validation. An attacker who controls content on a crawled page could include links to domains that share a string prefix with the target, causing the crawler to follow links to attacker-controlled or internal infrastructure. Additionally, the crawler performed no validation against private or reserved IP addresses. A crawled page could include links targeting cloud metadata services, localhost, or RFC 1918 addresses, and the crawler would fetch them without restriction. This vulnerability is fixed in 1.1.14.

Metrics

CVSS 3.1

4.1/10

CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:N/A:N

EPSS Probability

0.37%

29.0th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

CWE-918

Affected Software

Vendor	Product	Versions
Langchain	Langchain Community	< 1.1.14

References

https://github.com/langchain-ai/langchainjs/commit/d5e3db0d01ab321ec70a875805b2f74aefdadf9dPatch
https://github.com/langchain-ai/langchainjs/pull/9990Issue Tracking, Patch
https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.14Release Notes
https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-gf3v-fwqg-4vh7Vendor Advisory

Timeline

Published: Feb 11, 2026
Last Modified: Jun 17, 2026
Status: Analyzed

Frequently Asked Questions

What is CVE-2026-26019?

LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/community is a web crawler that recursively follows links from a starting URL. Its preventOutside option (enabled by default) is intended to restrict crawling to the same site as the base URL. The implementation used String.startsWith() to compare URLs, which does not perform semantic URL validation. An attacker who controls content on a crawled page could include links to domains that share a string prefix with the target, causing the crawler to follow links to attacker-controlled or internal infrastructure. Additionally, the crawler performed no validation against private or reserved IP addresses. A crawled page could include links targeting cloud metadata services, localhost, or RFC 1918 addresses, and the crawler would fetch them without restriction. This vulnerability is fixed in 1.1.14.

How severe is CVE-2026-26019?

CVE-2026-26019 has a CVSS score of 4.1/10 (MEDIUM severity). The EPSS model estimates a 0.37% probability of exploitation in the next 30 days.

How do I fix CVE-2026-26019?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.