CVE-2026-44843
Fixed in a distro release EPSS <1%CVSS 8.2
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.
Products: langchain-ai langchain
Fixed upstream
| Ecosystem | Package | Fixed in |
|---|---|---|
| PyPI | langchain-core | 1.3.3 |
| PyPI | langchain-core | 0.3.85 |
Distro releases
| Release | Package | Fixed in |
|---|---|---|
| Chainguard | py3-langchain | 1.3.4-r0 |
| Chainguard | py3.10-langchain | 1.3.4-r0 |
| Chainguard | py3.10-langchain-core | 1.4.0-r0 |
| Chainguard | py3.11-langchain | 1.3.4-r0 |
| Chainguard | py3.11-langchain-core | 1.4.0-r0 |
| Chainguard | py3.12-langchain | 1.3.4-r0 |
| Chainguard | py3.12-langchain-core | 1.4.0-r0 |
| Chainguard | py3.13-langchain | 1.3.4-r0 |
| Chainguard | py3.13-langchain-core | 1.4.0-r0 |