CVE-2026-44843Network attack vector

Object injection via overly broad deserialization allowlist

Published May 26, 2026 · Updated May 26, 2026

Unsafe deserialization in LangChain Core before 0.3.85 and 1.0.0 through 1.3.2 allows remote attackers to revive trusted objects. Affected runtime paths pass preserved nested run data to load() with allowed_objects="all", instantiating allowlisted classes with untrusted constructor arguments instead of preserving inert data. Exposure requires untrusted structured input to remain nested and reach an affected runtime path; bounded impacts include chat-history poisoning, prompt manipulation, credential disclosure, or server-side requests.

CVSS severity8.2
High
EPSS probability0.41%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Unsafe deserialization in LangChain Core before 0.3.85 and 1.0.0 through 1.3.2 allows remote attackers to revive trusted objects. Affected runtime paths pass preserved nested run data to load() with allowed_objects="all", instantiating allowlisted classes with untrusted constructor arguments instead of preserving inert data. Exposure requires untrusted structured input to remain nested and reach an affected runtime path; bounded impacts include chat-history poisoning, prompt manipulation, credential disclosure, or server-side requests.

The record

CVE
CVE-2026-44843
Published
May 26, 2026
Updated
May 26, 2026
Vendor
LangChain
Product
LangChain
Classifications
CWE-502, T1190
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. May 26, 2026CVE publishedPublication date reported by the CVE source.
  2. May 26, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=< 0.3.85
  2. Affected versionversion=>= 1.0.0a1, < 1.3.3

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

LangChain · LangChainversion=< 0.3.85; version=>= 1.0.0a1, < 1.3.3

Published CVSS scores

8.2GitHub, Inc.CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 9, 2026Sep 15, 2026
Latest reporting daySep 15, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-502Deserialization of Untrusted Data
T1190Exploit Public-Facing Application

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo