- CVSS
- MEDIUM · 4.1 v3.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:N/A:N
- Published
- 2026-02-11
- Weakness
- CWE-918
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-26019
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.
References
- https://github.com/langchain-ai/langchainjs/commit/d5e3db0d01ab321ec70a875805b2f74aefdadf9d
- https://github.com/langchain-ai/langchainjs/pull/9990
- https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.14
- https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-gf3v-fwqg-4vh7
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-26019 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.