CVE-2026-34070
Medium
Elevated severity or exploit probability.
CVSS base
7.5
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
EPSS — probability of exploitation (30 days)
1.2%
67.2th percentile
CISA KEV
Not listed
Weakness / dates
CWE-22
Published 2026-03-31 · modified 2026-08-25
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
References
- https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c
- https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22
- exploit https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54
- https://access.redhat.com/errata/RHSA-2026:24766
- https://access.redhat.com/errata/RHSA-2026:37275
- https://access.redhat.com/errata/RHSA-2026:59159
- https://access.redhat.com/security/cve/CVE-2026-34070
- https://bugzilla.redhat.com/show_bug.cgi?id=2453287
- exploit https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34070.json