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.
Affected products
langchain: langchain core
References10
- github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h… ExploitVendor Advisory
- github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h… ExploitVendor Advisory
- github.com/langchain-ai/langchain/commit/27add913474e01e33beded… Patch
- github.com/langchain-ai/langchain/releases/tag/langchain-core==… Release Notes
- access.redhat.com/errata/RHSA-2026:24766
- access.redhat.com/errata/RHSA-2026:37275
- access.redhat.com/errata/RHSA-2026:59159
- access.redhat.com/security/cve/CVE-2026-34070
- bugzilla.redhat.com/show_bug.cgi?id=2453287
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34070…
Metrics
- CVSS 3.1
-
7.5
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - EPSS — exploit probability
- 1% percentile: 73 · as of 12 November 2026
- CWE
- CWE-22
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.