Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agent Safehouse – macOS-native sandboxing for local agents

agent-safehouse.dev

Post reply on HN
Print view View original

161–170 of 207 posts

Re: Agent Safehouse – macOS-native sandboxing for local agents

#161

Post by andai »

I was obstinate and refused to learn docker, so I realized I can just rent a $3 VPS. If it blows up the VPS I reset it!

Then I realized the only thing I care about on my local machine is "don't touch my files", and Unix users solved that in 1970. So I just run agents as "agent" user.

I think running it on a separate machine is nicer though, because it's even simpler and safer than that. (My solution still requires careful setup and regular overhead when you get permission issues. "It's on another laptop, and my stuff isn't" has neither of those problems.)

Re: Agent Safehouse – macOS-native sandboxing for local agents

#163

Post by chrisweekly »

e1g wrote: post #134
oneplane wrote: post #82

Earlier quoted context omitted.

That online builder is very cool, well done! I've been trying out similar things to help internal teams to use systems and languages like Rego (for Open Policy Agent) to have a visual and more 'a la carte' experience when starting out, so they don't have to jump straight to learning all syntax and patterns for a language they might have never seen before.

Thanks, Codex helped to put that together in like 20 minutes. Try feeding your agent the idea about an interactive config builder, give it the upstream URL with your condos, and see if it can whip up something for you.

condos?

Re: Agent Safehouse – macOS-native sandboxing for local agents

#166

Post by terhechte »

mkagenius wrote: post #31

A way to run claude code inside a apple container - $ container system start $ container run -d --name myubuntu ubuntu:latest sleep infinity $ container exec myubuntu bash -c "apt-get update -qq && apt-get install -y openssh-server" $ container exec myubuntu bash -c " apt-get install -y curl && curl -fsSL https://deb.nodesource.com/setup_lts.x | bash - && apt-get install -y nodejs " $ container exec myubuntu npm inst…

Shuru should do exactly what you want:

https://shuru.run

Re: Agent Safehouse – macOS-native sandboxing for local agents

#168

Post by llimllib »

w10-1 wrote: post #102

But... why not just run macOS in a VM? If/since AI agents work continuously, it seems like running macOS in a VM (via the virtualization framework directly) is the most secure solution and requires a lot less verification than any sandboxing script. (Critical feature: no access to my keychain.) AI agents are not at all like container deploys which come and go with sub-second speed, and need to be small enough that yo…

For me, it's file system latency on mac os when virtualizing that kills me. Cargo, npm, pip, etc create many small files and there's a high per-file latency on the FS layer

Re: Agent Safehouse – macOS-native sandboxing for local agents

#169

Post by tcbrah »

ptak_dev wrote: post #153

[flagged]

problem 2 is actually scarier than most people realize because it compounds. your agent reads a README in some dependency, that README has injection instructions, now the agent is acting on behalf of the attacker with whatever permissions you gave it. filesystem sandboxing doesnt help because the dangerous action might be "write a backdoor into the file i already have write access to" which is completely within the sandbox rules.

the short-lived scoped credentials approach someone mentioned upthread is probably the best practical mitigation right now. but even that breaks down when the agent legitimately needs broad access to do its job - like if its refactoring across a monorepo it kinda needs write access to everything.

i think the actual answer long term is something closer to capability-based security where each tool call gets its own token scoped to exactly what that specific action needs. but nobody has built that yet in a way that doesnt make the agent 10x slower.

Post reply on HN