Vulnerability · Published Mar 5, 2026 · Assigned by GitHub_M
CVE-2026-28277LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loading
Medium 6.8
In plain English
A medium-severity unsafe deserialization in langgraph from langchain-ai. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 5.5% (higher than 93% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | langgraph | 1.0.10 | GHSA-g48c-2wqr-h844 |
| PyPI | langgraph | 1.0.10rc1 | PYSEC-2026-83 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| langchain-ai | langgraph | <= 1.0.9 |
Weakness: CWE-502 · Vector: CVSS:3.1/AV:A/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H