Authenticated code execution via unrestricted constructor deserialization
Published Nov 7, 2025 · Updated Nov 7, 2025
Remote code execution in LangChain LangGraph before 3.0.0 allows remote authenticated users to execute Python code via crafted checkpoints. JsonPlusSerializer's JSON reviver accepts lc=2 constructor records and resolves their id paths to arbitrary callables instead of restricting allowed types. Exploitation requires an application to persist attacker-supplied checkpoint data in JSON mode, reached explicitly or after MessagePack rejects an illegal Unicode surrogate.
Summary
What happened
Remote code execution in LangChain LangGraph before 3.0.0 allows remote authenticated users to execute Python code via crafted checkpoints. JsonPlusSerializer's JSON reviver accepts lc=2 constructor records and resolves their id paths to arbitrary callables instead of restricting allowed types. Exploitation requires an application to persist attacker-supplied checkpoint data in JSON mode, reached explicitly or after MessagePack rejects an illegal Unicode surrogate.
The record
- CVE
- CVE-2025-64439
- Published
- Nov 7, 2025
- Updated
- Nov 7, 2025
- Vendor
- LangChain
- Product
- LangGraph
- Classifications
- CWE-502, CAPEC-586, T1059.006
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Nov 7, 2025CVE publishedPublication date reported by the CVE source.
- Nov 7, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 3.0.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA constructor-deserialization proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo