CVE-2026-44843

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

HIGH

8.2

CVSS Score

Published: May 26, 2026 at 07:47 PM UTC

Updated: July 24, 2026 at 11:10 AM UTC

2 products affected across 2 vendorsLangchainLangChain

Using langchain by langchain-ai?

Get instant alerts when new vulnerabilities affect langchain - before attackers find them.

Real-time alertsTrack your software stackFree plan available

Start Free Sign In

Severity

HIGH8.2

Exploit prediction

EPSS 0.4%

SSVC

No known exploit

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.

Affected

Our own answer: ranges merged, affected separated from platform-only, with confidence and review flags.

Langchain · Langchain

95%

v < 0.3.851.0.0 ≤ v < 1.3.3

Affected range stops below 0.3.85, so it looks safe — our inference, not a vendor statement

Affected range stops below 1.3.3, so it looks safe — our inference, not a vendor statement

LangChain · Langchain AI

60%

v < 0.3.85v < 1.3.3

Affected range stops below 0.3.85, so it looks safe — our inference, not a vendor statement

Affected range stops below 1.3.3, so it looks safe — our inference, not a vendor statement

Remediation

No guide yet

No remediation guidance has been written for this CVE yet. What the record does show:

Patch and advisory references

https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724

References (1)

x_refsource_CONFIRMMitigationVendor Advisory

Source: cverecord

https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724

SSVC — Action Prioritization

SSVCNo known exploitAutomatablePartial impact

SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.

CVSS

8.2HIGHGitHub_M

Attack Vector: NETWORK
Complexity: LOW
Privileges: NONE
User Interaction: NONE
Scope: UNCHANGED
Confidentiality: HIGH
Integrity: LOW
Availability: NONE

Vector?

Quick Info

StatusANALYZED

CWE

CWE-502

Get alerted

Stop reading CVE feeds looking for your own stack

Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.

Create account Sign in

Free plan, no card