7.2

CVE-2026-28277: langchain-ai langgraph Deserialization of Untrusted Data

CVSS: 7.2v3.1HighAnalyzed
AliasesGHSA-g48c-2wqr-h844PYSEC-2026-83
Published 05-03-2026Last modified 06-03-2026

Vulnerability summary

CVE-2026-28277 is a high (CVSS 7.2) Deserialization of Untrusted Data vulnerability in langchain-ai langgraph. EPSS estimates a 0.70% chance of exploitation in the next 30 days, higher than 52.2% of scored vulnerabilities.

Overall risk
29/100
0100
Medium · default modelHow is this calculated?
CVSS score
7.2/10
010
High · v3.1 (NVD)
EPSS score
0.70%
0%100%
Low · -4.23 pp in 30 days
KEVNot listedIn no KEV catalog
RansomwareNone recordedNo known use recorded
Public exploits0No public exploits recorded

Timeline

  1. 05-03-2026
    PublishedVulnerability first disclosed.
  2. 06-03-2026
    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 version 1.0.9 and prior, LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can modify checkpoint data in the backing store (for example, after a database compromise or other privileged write access to the persistence layer), they can potentially supply a crafted payload that triggers unsafe object reconstruction when the checkpoint is loaded. No known patch is public.

CVSS metrics

3 scores · 3 sources · 1 version

EPSS trend

Probability

0.70%

Chance of exploitation in the next 30 days

Percentile

52%

Versus all other CVEs

30-day change

-4.23 pp

From 4.93% on 19-09-2026

19-09-202619-10-2026
EPSS score
0.70%

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

Langchain1 product
Langchain-ai1 product
PyPI1 product
  • langgraph< 1.0.10 | < 1.0.10rc1

3 vendors · 3 products

References

4 links