Hacker News new | ask | show | jobs
AI Agent Sandboxes Got Security Wrong (multikernel.io)
3 points by wang_cong 79 days ago
1 comments

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.