CVE-2026-44843

8.2 HIGH
Published: May 26, 2026 Modified: May 29, 2026
View on NVD

Description

LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3.

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

Login to generate AI explanation

CVSS v3.x Details

0.0 Low Medium High Critical 10.0
Vector String
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory
https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724
Source: security-advisories@github.com
Mitigation Vendor Advisory

1 reference(s) from NVD

Quick Stats

CVSS v3 Score
8.2 / 10.0
EPSS (Exploit Probability)
0.0%
14th percentile
Exploitation Status
Not in CISA KEV

Weaknesses (CWE)

Affected Vendors

langchain