CVE-2026-34070

  1. OpenCVE
  2. Vulnerabilities (CVE)
  3. CVE-2026-34070
LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.

7.5 /10

CVSS v3 : HIGH

V3 Legend

Vector :

Exploitability : 3.9 / Impact : 3.6

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact NONE

Availability Impact NONE

Scope UNCHANGED

References
Link Resource
https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c Patch
https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22 Release Notes
https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54 Exploit Vendor Advisory
https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54 Exploit Vendor Advisory
Configurations

Configuration 1 (hide)

cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*
History

02 Apr 2026, 17:04

Type Values Removed Values Added
References () https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c - () https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c - Patch
References () https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22 - () https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22 - Release Notes
References () https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54 - () https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54 - Exploit, Vendor Advisory
CPE cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*
First Time Langchain langchain
Langchain

31 Mar 2026, 18:16

Type Values Removed Values Added
Summary
  • (es) LangChain es un framework para construir agentes y aplicaciones impulsadas por LLM. Antes de la versión 1.2.22, múltiples funciones en langchain_core.prompts.loading leían archivos de rutas incrustadas en diccionarios de configuración deserializados sin validar contra salto de directorio o inyección de ruta absoluta. Cuando una aplicación pasa configuraciones de prompt influenciadas por el usuario a load_prompt() o load_prompt_from_config(), un atacante puede leer archivos arbitrarios en el sistema de archivos del host, restringido solo por verificaciones de extensión de archivo (.txt para plantillas, .json/.yaml para ejemplos). Este problema ha sido parcheado en la versión 1.2.22.
References () https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54 - () https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54 -

31 Mar 2026, 03:15

Type Values Removed Values Added
New CVE
Information

Published : 2026-03-31 03:15

Updated : 2026-04-02 17:04

NVD link : CVE-2026-34070

Mitre link : CVE-2026-34070

CVE.ORG link : CVE-2026-34070

JSON object : View

Products Affected

langchain

  • langchain
CWE
CWE-22

Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')