CVE-2025-64439: LangGraph Checkpoint Affected by RCE
Affects langgraph-checkpointSource GCVE Database
Not known to be exploited · CVSS 7.4 High : upgrade to 3.0.0 soon.
Data as of 4 Nov 2026, 18:52 UTC
Thin evidence
One scorer or none| CNA (GitHub_M) | CVSS 4.0 | 7.4 |
|---|
- Patch
- Available – fixed in 3.0.0
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:HExploitation evidence
Disclosed: evidence found.
CVE published 7 Nov 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 4 Nov 2026.
What to do
Upgrade langgraph-checkpoint to 3.0.0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| PyPIlanggraph-checkpoint | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Upgrade immediately to langgraph-checkpoint version 3.0.0 or later, which includes an allow-list for safe constructor deserialization and removes the unsafe fallback to "json" mode. For users of langgraph-api, upgrading to version 0.5 or later ensures the patched checkpointer is used. No code changes or import modifications are required for compatibility with the fixed version.
Description
LangGraph Checkpoint versions prior to 3.0.0 contain a remote code execution (RCE) vulnerability in the JsonPlusSerializer when deserializing payloads in the "json" serialization mode. This occurs because the deserializer supports a constructor-style format that can execute arbitrary Python code if malicious payloads are deserialized. The vulnerability is fixed in version 3.0.0 by introducing an allow-list for constructor deserialization and deprecating the unsafe "json" fallback mode. Users of langgraph-api version 0.5 or later are also not affected.
References
- github.com/langchain-ai/langgraph/security/advisories/GHSA-wwqv-p2pp-99h5 (opens in a new tab)
- nvd.nist.gov/vuln/detail/CVE-2025-64439 (opens in a new tab)
- github.com/langchain-ai/langgraph/commit/c5744f583b11745cd406f3059903e17bbcdcc8ac (opens in a new tab)
- github.com/langchain-ai/langgraph (opens in a new tab)
- github.com/langchain-ai/langgraph/blob/c5744f583b11745cd406f3059903e17bbcdcc8ac/libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py (opens in a new tab)
- github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D3.0.0 (opens in a new tab)