8.2High

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

langchain-ai langchain Published: (5 months ago)

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.

Weakness (CWE): CWE-502

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
langchain langchain < 0.3.85
langchain-ai langchain < 0.3.85, >= 1.0.0a1, < 1.3.3

References and patches

CPE matches (NVD) (2)

  • cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:* < 0.3.85
  • cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:* ≥ 1.0.0 < 1.3.3