Vulnerability 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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Langchain | Langchain | < 0.3.85 |
Related Weaknesses (CWE)
References
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-772MitigationVendor Advisory
FAQ
What is CVE-2026-44843?
CVE-2026-44843 is a vulnerability with a CVSS score of 8.2 (HIGH). 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 app...
How severe is CVE-2026-44843?
CVE-2026-44843 has been rated HIGH with a CVSS base score of 8.2/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-44843?
Check the references section above for vendor advisories and patch information. Affected products include: Langchain Langchain.