CVE-2026-26013

  1. OpenCVE
  2. Vulnerabilities (CVE)
  3. CVE-2026-26013
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability is fixed in 1.2.11.

3.7 /10

CVSS v3 : LOW

V3 Legend

Vector :

Exploitability : 2.2 / Impact : 1.4

Attack Vector NETWORK

Attack Complexity HIGH

Privileges Required NONE

User Interaction NONE

Confidentiality Impact NONE

Integrity Impact NONE

Availability Impact LOW

Scope UNCHANGED

References
Link Resource
https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565 Patch
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11 Product Release Notes
https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r Mitigation Vendor Advisory
Configurations

Configuration 1 (hide)

cpe:2.3:a:langchain:langchain_core:*:*:*:*:*:python:*:*
History

17 Mar 2026, 20:30

Type Values Removed Values Added
References () https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565 - () https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565 - Patch
References () https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11 - () https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11 - Product, Release Notes
References () https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r - () https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r - Mitigation, Vendor Advisory
Summary
  • (es) LangChain es un framework para construir agentes y aplicaciones impulsadas por LLM. Antes de la versión 1.2.11, el método ChatOpenAI.get_num_tokens_from_messages() obtiene valores arbitrarios de image_url sin validación al calcular el recuento de tokens para modelos habilitados para visión. Esto permite a los atacantes desencadenar ataques de falsificación de petición del lado del servidor (SSRF) al proporcionar URLs de imagen maliciosas en la entrada del usuario. Esta vulnerabilidad está corregida en la versión 1.2.11.
First Time Langchain langchain Core
Langchain
CPE cpe:2.3:a:langchain:langchain_core:*:*:*:*:*:python:*:*

10 Feb 2026, 22:17

Type Values Removed Values Added
New CVE
Information

Published : 2026-02-10 22:17

Updated : 2026-03-17 20:30

NVD link : CVE-2026-26013

Mitre link : CVE-2026-26013

CVE.ORG link : CVE-2026-26013

JSON object : View

Products Affected

langchain

  • langchain_core
CWE
CWE-918

Server-Side Request Forgery (SSRF)