VulnerabilityModified

CVE-2026-34070

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.

HIGH 7.5EPSS 1.38%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (1.38%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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.

CVSS 3.1: 7.5 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
EPSS: 1.38% probability · 71th percentile
CISA KEV: Not listed
Weakness: CWE-22
Affected: langchain/langchain core
Source: security-advisories@github.com

References

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.