LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists
Summary
| CVE | CVE-2026-44843 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-05-26 21:16:39 UTC |
| Updated | 2026-05-29 19:48:48 UTC |
| 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. |
Risk And Classification
Primary CVSS: v3.1 8.2 HIGH from [email protected]
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
EPSS: 0.000450000 probability, percentile 0.141500000 (date 2026-06-02)
Problem Types: CWE-502 | CWE-502 CWE-502: Deserialization of Untrusted Data
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 3.1 | [email protected] | Secondary | 8.2 | HIGH | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N |
| 3.1 | CNA | DECLARED | 8.2 | HIGH | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N |
CVSS v3.1 Breakdown
Attack Vector
NetworkAttack Complexity
LowPrivileges Required
NoneUser Interaction
NoneScope
UnchangedConfidentiality
HighIntegrity
LowAvailability
NoneCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
NVD Known Affected Configurations (CPE 2.3)
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | Langchain-ai | Langchain | affected < 0.3.85 | Not specified |
| CNA | Langchain-ai | Langchain | affected >= 1.0.0a1, < 1.3.3 | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724 | [email protected] | github.com | Mitigation, Vendor Advisory |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.