CVE-2026-28277: LangGraph Unsafe Msgpack Deserialization Vulnerability
Summary
CVE-2026-28277: LangGraph checkpoint loading has unsafe msgpack deserialization. Affects langgraph versions < 1.0.9. No fix is published. How to fix ↓
Check if this vulnerability affects your application
Upload a manifest or SBOM and we'll show whether you're affected, plus every other risky package in the same scan.
No signup required · Results in about 60 seconds
Habilume
Habit tracker with a companion that grows with you
Complete habits, earn Lume Points, and watch your Lume grow as you stay consistent.
Background
LangGraph is an open-source library designed for building and managing stateful applications using graphs. It allows users to create complex workflows and manage data efficiently. However, LangGraph has a vulnerability related to its checkpoint loading mechanism, which can lead to unsafe deserialization of msgpack-encoded data, potentially allowing attackers to execute arbitrary code.
Vulnerability Detail
The vulnerability arises from LangGraph's ability to load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker gains privileged write access to the checkpoint data, they can modify it to include a crafted payload that triggers unsafe object reconstruction. This poses a significant risk as it can escalate from mere write access to code execution within the application runtime, potentially exposing sensitive information such as environment variables and cloud credentials.
How To Fix
No fixed version is published for this vulnerability.
Tip — Not sure whether your app is affected? Vulert can check the versions your app actually runs. Scan free →
Workaround
As a temporary workaround, users can restrict write access to the checkpoint store and rotate credentials if a compromise is suspected. Furthermore, avoid using custom msgpack deserialization hooks that reconstruct arbitrary types unless the checkpoint data is fully trusted.
Conclusion
The LangGraph vulnerability (CVE-2026-28277) poses a significant risk due to unsafe msgpack deserialization, which can lead to arbitrary code execution if checkpoint data is compromised. Users are advised to update to the latest version and implement strict deserialization policies to mitigate risks.
See every vulnerability recorded for langgraph →
FAQ
The CVSS score of this vulnerability is 6.8, indicating a moderate severity level.
You can use Vulert's playground at Vulert Scanner to check if your application is affected by this vulnerability without needing to sign up.
The potential consequences include arbitrary code execution, exposure of sensitive runtime secrets, and escalation of privileges from write access to code execution.
As of now, there is no evidence of exploitation in the wild, and LangGraph is not aware of any practical exploitation paths in existing deployments.
If you cannot update immediately, ensure that you restrict write access to the checkpoint store and enable strict mode for msgpack deserialization as a temporary measure.
References
Related vulnerabilities
Recent vulnerabilities recorded for langgraph.
Habilume
Habit tracker with a companion that grows with you
Complete habits, earn Lume Points, and watch your Lume grow as you stay consistent.
