Read the docs
TI-2026-32721 Aliases CVE-2026-44843GHSA-pjwx-r37v-7724

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

Priority MEDIUM 42CWE-502Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Impact type
Code execution
Confidentiality · integrity · availability
High · Low · None
Fix status
Partial Red Hat: 3 fixed, 4 without a fix

Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-502.

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00406 35th percentileScored 2026-11-07
Fix Partial langchain (langchain-ai): 0.3.85, 1.3.3langchain-core (PyPI): 1.3.3, 0.3.85Red Hat: 4 advisoriesRed Hat: 3 fixed, 4 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
Yes
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
langchain-ailangchainbefore 0.3.85; 1.0.0a1 to before 1.3.30.3.85, 1.3.3Patch availableCNA
—langchain-core (PyPI)1.0.0 to before 1.3.31.3.3Patch availableGHSA-pjwx-r37v-7724
—langchain-core (PyPI)before 0.3.850.3.85Patch availableGHSA-pjwx-r37v-7724
  • langchain Vendorlangchain-ai Affected before 0.3.85; 1.0.0a1 to before 1.3.3 Fixed in 0.3.85, 1.3.3 Patch available CNA
  • langchain-core (PyPI) Vendor— Affected 1.0.0 to before 1.3.3 Fixed in 1.3.3 Patch available GHSA-pjwx-r37v-7724
  • langchain-core (PyPI) Vendor— Affected before 0.3.85 Fixed in 0.3.85 Patch available GHSA-pjwx-r37v-7724

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*before 0.3.85; 1.0.0 to before 1.3.3Vulnerablelangchain-ai
  • cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:* Versions before 0.3.85; 1.0.0 to before 1.3.3 Vulnerable ·langchain-ai

Remediation

  • Fix · CNA langchain (langchain-ai) Fixed in 0.3.85, 1.3.3
  • Fix · GHSA-pjwx-r37v-7724 langchain-core (PyPI) Fixed in 1.3.3 Advisory →
  • Fix · GHSA-pjwx-r37v-7724 langchain-core (PyPI) Fixed in 0.3.85 Advisory →

Red Hat 4 advisories

  • RHSA-2026:84734 Released 2026-10-19 · Red Hat rating Critical
    RHOAI 3.4.5 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 3.4 registry.redhat.io/rhoai/odh-ai-gateway-payload-processing-rhel9, registry.redhat.io/rhoai/odh-automl-rhel9, registry.redhat.io/rhoai/odh-autorag-rhel9 +47
  • RHSA-2026:73987 Released 2026-09-30 · Red Hat rating Critical
    RHOAI 3.3.7 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 3.3 registry.redhat.io/rhoai/odh-built-in-detector-rhel9, registry.redhat.io/rhoai/odh-dashboard-rhel9, registry.redhat.io/rhoai/odh-data-science-pipelines-argo-argoexec-rhel9 +47
  • RHSA-2026:60520 Released 2026-08-27 · Red Hat rating Critical
    RHOAI 3.4.4 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 3.4 registry.redhat.io/rhoai/odh-automl-rhel9, registry.redhat.io/rhoai/odh-autorag-rhel9, registry.redhat.io/rhoai/odh-built-in-detector-rhel9 +47
Show 1 more Red Hat advisories
  • RHSA-2026:43038 Released 2026-07-21 · Red Hat rating Critical
    Migration Toolkit for Applications
    • Red Hat Migration Toolkit for Applications 8.2 registry.redhat.io/mta/mta-cli-rhel9, registry.redhat.io/mta/mta-solution-server-rhel9

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
Exploit IntelligenceAffectedNo fix yet
OpenShift LightspeedAffectedNo fix yet
Red Hat Ansible Automation Platform 2AffectedNo fix planned: Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet
Red Hat Migration Toolkit for Applications 8.2Fixed RHSA-2026:43038
Red Hat OpenShift AI 3.3Fixed RHSA-2026:73987
Red Hat OpenShift AI 3.4Fixed RHSA-2026:60520, RHSA-2026:84734
Not affected: 3 products
  • Red Hat Migration Toolkit for Applications 8.2
  • Red Hat OpenShift AI 3.3
  • Red Hat OpenShift AI 3.4

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-44843
  2. 2026-10-03 Alias added: GHSA-pjwx-r37v-7724
  3. 2026-10-07 Fix available: RHSA-2026:73987 · Red Hat
  4. 2026-10-20 Fix available: RHSA-2026:84734 · Red Hat
  5. 2026-10-20 Affected versions changed · Red Hat

References

Advisory 2

Other 1

  • TI-2023-20724 An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to… CVSS 3.1CRITICAL 9.8
  • TI-2023-20706 An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary… CVSS 3.1CRITICAL 9.8
  • TI-2023-20166 An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to… CVSS 3.1CRITICAL 9.8
  • TI-2023-20136 An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter. CVSS 3.1CRITICAL 9.8
  • TI-2023-18185 An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a… CVSS 3.1CRITICAL 9.8
  • TI-2023-18176 An issue in LangChain before 0.0.236 allows an attacker to execute arbitrary code because… CVSS 3.1CRITICAL 9.8
See all 27 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences