7.4

CVE-2025-64439: langchain-ai langgraph Deserialization of Untrusted Data

CVSS: 7.4v4.0HighDeferred
AliasesGHSA-wwqv-p2pp-99h5PYSEC-2026-1527
Published 07-11-2025Last modified 07-11-2025

Vulnerability summary

CVE-2025-64439 is a high (CVSS 7.4) Deserialization of Untrusted Data vulnerability in langchain-ai langgraph. EPSS estimates a 0.89% chance of exploitation in the next 30 days, higher than 58.6% of scored vulnerabilities.

Overall risk
30/100
0100
Medium · default modelHow is this calculated?
CVSS score
7.4/10
010
High · v4.0 (CVE.org)
EPSS score
0.89%
0%100%
Low · 0.00 pp in 30 days
KEVNot listedIn no KEV catalog
RansomwareNone recordedNo known use recorded
Public exploits0No public exploits recorded

Timeline

  1. 07-11-2025
    PublishedVulnerability first disclosed.
  2. 07-11-2025
    Last modifiedVulnerability information updated.

Description

LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the "json" serialization mode. By default, the serializer attempts to use "msgpack" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the "json" mode. This issue is fixed in version 3.0.0.

CVSS metrics

3 scores · 3 sources · 1 version

EPSS trend

Probability

0.89%

Chance of exploitation in the next 30 days

Percentile

59%

Versus all other CVEs

30-day change

0.00 pp

From 0.88% on 19-09-2026

19-09-202619-10-2026
EPSS score
0.89%

Known exploited

Compare KEV catalogs

Not in any of the 3 tracked catalogs.

Public exploits

0 found

No public exploits indexed.

Weaknesses

CWE · root cause

Affected systems

Langchain-ai1 product
PyPI1 product
  • langgraph-checkpoint< 3.0.0

2 vendors · 2 products

References

8 links