CVE-2026-48775 LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loading
An attacker with write access to the SQLite checkpoint store can achieve code execution via unsafe JSON deserialization in LangGraph.
- Exploited in the wild
- Not known
- Login needed
- An administrator
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-48775?
CVE-2026-48775 is a medium-severity unsafe deserialization vulnerability in langchain-ai langgraph, published on 16 Jun 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official description
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 4.1.0 and prior, the JsonPlusSerializer can reconstruct Python objects from JSON checkpoint payloads. Under conditions where someone could modify checkpoint bytes at rest in the backing store, the deserialization path could reconstruct objects beyond what the application expects, which could in turn result in code execution at checkpoint load time. This is a defense-in-depth issue. The affected behavior is reachable only when checkpoint bytes at rest in the backing store can be modified by an unauthorized party. In most deployments that prerequisite already implies a serious incident; the additional concern is turning "checkpoint-store write access" into code execution in the application runtime. This issue has been fixed in version 4.1.1.
Which versions are affected by CVE-2026-48775?
3 open source packages ship an affected version, including langgraph-checkpoint. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
langgraph-checkpoint PyPI | All versions | 4.1.1 |
langgraph-checkpoint PyPI | All versions | 4.1.1 |
langgraph-checkpoint PyPI | All versions | 4.1.1 |
Products include Langchain Langgraph-Checkpoint.
How do I fix CVE-2026-48775?
Upgrade langgraph-checkpoint to 4.1.1 or later.
Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.
Is CVE-2026-48775 being exploited?
There is no known exploitation of CVE-2026-48775 in the wild and no public exploit code.
Sources
Also known as CLSA-2026-1783472544, GHSA-fjqc-hq36-qh5p, PYSEC-2026-2573, ROOT-APP-PYPI-CVE-2026-48775.