Deserialization in Langchain
CVE-2026-44843
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.
Vulnerability class: Insecure Deserialization
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.2 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N.
EPSS exploit prediction
EPSS 0.004, 35.4th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Langchain
- Langchain-Ai Langchain — versions < 0.3.85, >= 1.0.0a1, < 1.3.3
Weakness classification (CWE)
References
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724 (Mitigation, Vendor Advisory)