cvedb.io
CVE-2026-34070
HIGH · CVSS 7.5
EPSS exploitation probability: 0%
Published 2026-03-31T03:15:58.947 · Last modified 2026-06-30T03:18:51.233

Summary

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.

Affected products

langchain — langchain_core

Does this affect you?

Add your gear to cvedb and we'll alert you only when langchain ships something exploited.

Check my exposure →

References

This product uses data from the NVD API but is not endorsed or certified by the NVD. Informational only; not professional security advice.