AI Agent Sandboxes Got Security Wrong(multikernel.io)

3 pointsby wang_congvor 3 Monaten1 comments

https://multikernel.io/2026/04/03/ai-agent-sandboxes-got-security-wrong/

3 comments

JSR_FDEDvor 3 Monaten

This is a fine start for filesystem and network policies. But before I’m ever going to be comfortable with an OpenClaw-like thing running on my system on my behalf, I’m going to want policies at an application level as well - which emails can be read, sent, deleted. Same for calendar entries and instant messaging, etc.

arian_vor 3 Monaten

_2fnrvor 3 Monaten