CVE-2026-44843LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists
Descripción
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.
Datos: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Se publican tal como los indican las fuentes, en inglés.
Productos y versiones afectados
| Fabricante | Producto | Versiones | |
|---|---|---|---|
| langchain | langchain | < 0.3.85 | |
| langchain-ai | langchain | < 0.3.85, >= 1.0.0a1, < 1.3.3 |
Referencias y parches
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724 MitigationVendor Advisory
Coincidencias CPE (NVD) (2)
cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*< 0.3.85cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*≥ 1.0.0 < 1.3.3