CVE-2026-44843
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.
Predictions
Heuristic predictions, AS-IS, for prioritization only.
Mitigations
Package impact
| Ecosystem | Package | Vulnerable | Fixed |
|---|---|---|---|
| PyPI | langchain-core | >=1.0.0,<1.3.3 | 1.3.3 |
| PyPI | langchain-core | <0.3.85 | 0.3.85 |
| PIP | langchain-core | <= 0.3.84 | 0.3.85 |
| PIP | langchain-core | >= 1.0.0, <= 1.3.2 | 1.3.3 |
References
CWEs
CWE-502
Community-verified mitigations for this CVE will appear above when contributors publish them.
Verify integrity in audit chain (admin only). AS-IS.