Is CVE-2026-34070 actively exploited?

No active exploitation of CVE-2026-34070 has been confirmed so far. Continue monitoring, as exploit status can change.

Can CVE-2026-34070 be exploited remotely?

Yes. CVE-2026-34070 is exploitable remotely over the network (CVSS attack vector: Network).

What is the CVSS score of CVE-2026-34070?

CVE-2026-34070 has a CVSS score of 7.5 (HIGH).

HOME VULNERABILITIESCVE-2026-34070

HIGH

CVE-2026-34070

CWE-22Published: March 31, 2026· Updated: Apr 2, 2026

7.5

CVSS v3.1

EPSS:0.19%probability of exploitation in 30 daysPercentile:41.1th

Official 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.

NVD Source

Technical Analysis

CVE-2026-34070 can be exploited remotely over the network without requiring physical or adjacent access, significantly expanding the attack surface for threat actors.

The vulnerability requires no privileges and no user interaction, making it a prime target for automated exploitation campaigns and worm-like propagation.

A successful exploit results in complete confidentiality breach (data exposure), with a CVSS base score of 7.5.