CVE-2026-44843 | LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists

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.

Published: 2026-05-26 Last update: 2026-05-29 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-44843 is rated Low Risk (33.5/100): CVSS High severity, with low exploitation likelihood (EPSS 0.01%). Monitor for updates and reassess as exploit intelligence or EPSS changes.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2026-44843

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-05-27 — 0.01% —

Full EPSS history (1 record total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-44843

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
8.2 3.1 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:L)
Attackers could change some data, but it’s limited—not everything goes.
Availability (A:N)
Service keeps running; no real outage angle.
 3.9 4.2 [email protected]

Weakness enumeration for CVE-2026-44843

GitHub Security Advisory for CVE-2026-44843

GHSA-pjwx-r37v-7724 · Severity: high · Ecosystem: pip — LangChain vulnerable to unsafe deserialization of attacker-controlled objects through overly broad `load()` allowlists

Affected software / configurations for CVE-2026-44843

Vendor Product Version Raw CPE
langchain langchain < 0.3.85 cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*
langchain langchain >= 1.0.0, < 1.3.3 cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*

References for CVE-2026-44843

cvelogic Threat Intelligence