Home

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.

PUBLISHED Reserved 2026-03-25 | Published 2026-03-31 | Updated 2026-03-31 | Assigner GitHub_M




HIGH: 7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Problem types

CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')

Product status

< 1.2.22
affected

References

github.com/...gchain/security/advisories/GHSA-qh6h-p6c9-ff54 exploit

github.com/...gchain/security/advisories/GHSA-qh6h-p6c9-ff54

github.com/...ommit/27add913474e01e33bededf4096151130ba0d47c

github.com/.../langchain/releases/tag/langchain-core==1.2.22

cve.org (CVE-2026-34070)

nvd.nist.gov (CVE-2026-34070)

Download JSON