← Back to CVEs

CVE-2026-34070

HIGH

7.5

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.

CVE Details

CVSS v3.1 Score7.5

SeverityHIGH

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

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionNONE

Published3/31/2026

Last Modified4/2/2026

Sourcenvd

Honeypot Sightings0

Affected Products

langchain:langchain

Weaknesses (CWE)

CWE-22

References

https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c(security-advisories@github.com)

https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22(security-advisories@github.com)

https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54(security-advisories@github.com)

https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54(134c704f-9b21-4f2e-91b3-4a467353bcc0)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.