Skip to content
Fencer Intel
high 8.2

CVE-2026-44843 json

LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists

published 6mo ago modified last mo. also EUVD-2026-31976 , GHSA-pjwx-r37v-7724 , PYSEC-2026-2564

cvss
8.2
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 35%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi langchain-core 0.3.85, 1.3.3
  • langchain langchain_core 0.3.85, 1.3.3

Is CVE-2026-44843 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-44843 updated cvss 8.2

langchain: LangChain: Information disclosure and data integrity compromise via insecure deserialization

  • Red Hat Exploit Intelligence exploit-intelligence-tech-preview/vulnerability-analysis-rhel9 Red Hat OpenShift Lightspeed openshift-lightspeed/lightspeed-service-api-rhel9
    affected: workaround, no fix available
  • Red Hat Ansible Automation Platform 2 ansible-automation-platform-24/lightspeed-rhel8, ansible-automation-platform-25/lightspeed-rhel8, ansible-automation-platform-25/lightspeed-chatbot-rhel8
    affected: workaround, no fix planned “Will not fix”
  • Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/disk-image-cuda-rhel9
    affected: workaround, no fix available, no fix planned “Will not fix”
  • Red Hat Migration Toolkit for Applications 8.2 mta/mta-solution-server-rhel9 1784109883
    fixed: vendor fix RHSA-2026:43038
  • Red Hat OpenShift AI 3.3 rhoai/odh-trustyai-nemo-guardrails-server-rhel9 1789570674
    fixed: vendor fix RHSA-2026:73987
  • Red Hat OpenShift AI 3.4 rhoai/odh-autorag-rhel9 1786612637, rhoai/odh-llama-stack-core-rhel9 1786635926, rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9 1791785804, rhoai/odh-trustyai-nemo-guardrails-server-rhel9 1787330585
    fixed: vendor fix RHSA-2026:60520
  • Red Hat Migration Toolkit for Applications 8.2 mta/mta-ui-rhel9 1783962515, mta/mta-cli-rhel9 1784211378, mta/mta-hub-rhel9 1784059743, mta/mta-rhel9-operator 1784219586, mta/mta-operator-bundle 1784220119, mta/mta-analyzer-addon-rhel9 1784163267, +7 more Red Hat OpenShift AI 3.3 rhoai/odh-cli-rhel9 1790070206, rhoai/rhai-cli-rhel9 1790070206, rhoai/odh-mlflow-rhel9 1789653606, rhoai/odh-trainer-rhel9 1790136369, rhoai/odh-maas-api-rhel9 1790131842, rhoai/odh-mlserver-rhel9 1789121365, +76 more Red Hat OpenShift AI 3.4 rhoai/odh-cli-rhel9 1787330837, rhoai/odh-cli-rhel9 1791509689, rhoai/rhai-cli-rhel9 1787330837, rhoai/rhai-cli-rhel9 1791509689, rhoai/odh-automl-rhel9 1786612415, rhoai/odh-automl-rhel9 1791535789, +202 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
partial
Assessed
5mo ago

Exploit prediction

0.41% chance of exploitation in the next 30 days, higher than 35% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CNA 3.1 8.2 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
GitHub 3.1 8.2 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
OSV 3.1 8.2 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

Affected packages

ecosystem package affected fixed in
pypi langchain-core
>=1.0.0, <1.3.3
<0.3.85
1.3.3
0.3.85

Affected products

  • langchain-ai langchain

Classification

Weakness
  • CWE-502 Deserialization of Untrusted Data

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.