What is the CVSS score of CVE-2026-26019?

CVE-2026-26019 has a CVSS 3.1 base score of 4.1 (Medium). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:N/A:N. EPSS exploitation probability: 0.0%.

Which versions of AI / ML are affected by CVE-2026-26019?

Organizations using is a framework for building LLM-powered applications. should be aware of moderate risk from CVE-2026-26019, a server-side request forgery vulnerability rated CVSS 4.1.. A patch is available.

How to fix or mitigate CVE-2026-26019?

Within 30 days: Identify affected systems running is a framework for building LLM-powered applications. and apply vendor patches as part of regular patch cycle. Vendor patch is available.

AI / ML CVE-2026-26019

MEDIUM

Server-Side Request Forgery (SSRF) (CWE-918)

2026-02-11 security-advisories@github.com

GHSA-gf3v-fwqg-4vh7

SSRF AI / ML Langchain Community Langchain Red Hat

4.1

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

4.1 MEDIUM

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

Red Hat

4.1 MEDIUM

qualitative

Primary rating from GitHub Advisory.

CVSS VectorGitHub Advisory

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

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

Required

Scope

Changed

Confidentiality

Low

Integrity

None

Availability

None

Lifecycle Timeline

Analysis Generated

Mar 12, 2026 - 22:02 vuln.today

Patch released

Feb 19, 2026 - 19:25 nvd

Patch available

CVE Published

Feb 11, 2026 - 22:15 nvd

MEDIUM 4.1

Blast Radius

ecosystem impact

† from your stack dependencies † transitive graph · vuln.today resolves 4-path depth

20 npm packages depend on @langchain/community (4 direct, 16 indirect)

Ecosystem-wide dependent count for version 1.1.14.

DescriptionGitHub Advisory

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.

AnalysisAI

RecursiveUrlLoader in LangChain Community prior to 1.1.14 uses weak string-based URL validation that allows attackers to bypass the preventOutside crawling restriction by crafting domains with matching prefixes, potentially exposing the crawler to malicious or internal infrastructure endpoints. An attacker controlling a crawled webpage could inject links to cloud metadata services or private IP ranges, which the crawler would follow without validation, leading to information disclosure.

Technical ContextAI

This vulnerability (CWE-918: Server-Side Request Forgery (SSRF)) affects Langchain Community. 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