aiqbench analysis
SideKernel addresses the critical security paradox where AI coding agents need autonomy but remain untrusted system components on local macOS machines. By leveraging microVMs to create a usable sandbox, this open-source solution directly tackles adoption barriers identified in user surveys, offering a practical alternative to cumbersome existing tools. This work advances the operational safety of local AI development environments without relying on cloud-based execution.
SideKernel: A Usable microVM Sandbox for AI Coding Agents on macOS
arXiv:2610.02456v1 Announce Type: cross Abstract: AI coding agents are untrusted system components, yet they require autonomy on the developer machines they run on. This contradiction is a security problem. Sandboxes provide an isolated environment, but for local macOS development, the existing local, open-source options for AI coding agents are few in number and cumbersome to use. I conducted a formative online user survey which indicates that fewer than 40% of AI coding agent users run their agents in a sandbox and identifies the top usability barriers hindering AI coding agent sandbox adoption. These findings are used to develop SideKernel: an open-source, local, microVM-based macOS sandbox for AI coding agents designed for usability. To evaluate SideKernel, I compiled a list of sandboxes available on the market and filtered it against five inclusion criteria. Then I performed a comparative analysis between SideKernel and the sandboxes that satisfy these criteria, across 23 capability tests derived from the usability barriers revealed by the user survey. I discovered that only a few sandboxes are similar to SideKernel, and that among those, Docker Sandboxes and SideKernel score highest on capability features related to usability. A secondary contribution of this paper is a survey of the existing solution space for local, open-source, microVM-based macOS sandboxes for AI coding agents.
Abstract:AI coding agents are untrusted system components, yet they require autonomy on the developer machines they run on. This contradiction is a security problem. Sandboxes provide an isolated environment, but for local macOS development, the existing local, open-source options for AI coding agents are few in number and cumbersome to use. I conducted a formative online user survey which indicates that fewer than 40% of AI coding agent users run their agents in a sandbox and identifies the top usability barriers hindering AI coding agent sandbox adoption. These findings are used to develop SideKernel: an open-source, local, microVM-based macOS sandbox for AI coding agents designed for usability. To evaluate SideKernel, I compiled a list of sandboxes available on the market and filtered it against five inclusion criteria. Then I performed a comparative analysis between SideKernel and the sandboxes that satisfy these criteria, across 23 capability tests derived from the usability barriers revealed by the user survey. I discovered that only a few sandboxes are similar to SideKernel, and that among those, Docker Sandboxes and SideKernel score highest on capability features related to usability. A secondary contribution of this paper is a survey of the existing solution space for local, open-source, microVM-based macOS sandboxes for AI coding agents.
17 pages, 5 figures, 9 tables. Georgia Tech M.S. Cybersecurity practicum project
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
arXiv:2610.02456 [cs.CR]
(or arXiv:2610.02456v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2610.02456 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 317 words
Related coverage

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

Top AI Coding Agents and Development Platforms in 2026: Atoms, Devin, Windsurf, Cursor, Warp, and More Compared
MarkTechPost · Jun 10, 2026

Kimi AI and kvcache-ai Open Sources ‘AgentENV’: A Distributed System that Powers Agentic Reinforcement Learning (RL) Training for Kimi K3
MarkTechPost · Jul 27, 2026

Critical Docker Sandbox Vulnerabilities Enable Malicious Guests to Escape Isolated microVM Workspaces
Cybersecurity News · Sep 17, 2026