Description

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.

INFO

Published Date :

2026-03-31T02:01:49.320Z

Last Modified :

2026-03-31T18:04:59.283Z

Source :

GitHub_M
AFFECTED PRODUCTS

The following products are affected by CVE-2026-34070 vulnerability.

Vendors Products
Langchain
  • Langchain
Langchain-ai
  • Langchain
REFERENCES

Here, you will find a curated list of external links that provide in-depth information to CVE-2026-34070.

URL Resource
https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c cve-icon cve-icon cve-icon
https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22 cve-icon cve-icon cve-icon
https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54 cve-icon cve-icon cve-icon cve-icon
https://nvd.nist.gov/vuln/detail/CVE-2026-34070 cve-icon
https://www.cve.org/CVERecord?id=CVE-2026-34070 cve-icon
Login to claim this CVE

CVSS Vulnerability Scoring System

Detailed values of each vector for above chart.
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality Impact
Integrity Impact
Availability Impact