GoKawiilMicrosoft open-sources MXC sandbox for running untrusted AI-generated code
Microsoft has released MXC (Microsoft eXecution Container), a sandboxed code execution system designed to run untrusted code such as model outputs, plugins and tools across Windows, Linux and macOS. It supports multiple containment backends—from lightweight process sandboxes to full microVMs like Hyperlight and Nanvix—configured through JSON-based policies covering filesystem, network and UI access, and is accessible via Rust, .NET and Node SDKs.
GoKawiil's interpretation of the reporting above, not reported fact.
As AI agents and plugins increasingly execute generated code, tooling like MXC could give developers a standardized way to contain potential damage from untrusted scripts rather than building bespoke sandboxes per platform. Offering multiple backend options suggests Microsoft is trying to balance security strength against performance and compatibility trade-offs for different use cases.
- MXC supports Windows, Linux and macOS with platform-specific sandboxing backends.
- Containers are configured via JSON policies controlling filesystem, network and UI access.
- SDKs are available in Rust, .NET, and Node for integrating the sandbox into applications.
Source: github.com, 2026-10-09
Published there as: “MXC - a sandboxed code execution system”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.