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

Description (CNA)

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 (CNA)

Vendor / product	Versions
langchain-ai / langchain	affected < 0.3.85; affected >= 1.0.0a1, < 1.3.3

CWE

CWE-502

References

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

ADP enrichment

CISA-ADP

No English description supplied.

No references supplied.