logoalt Hacker News

saagarjha • today at 3:01 AM • 14 replies • view on HN

I just don’t think I agree with these designs at all. Everyone seems to be super laser focused on “not allowing their AI to have keys” when basically giving their AI direct access to what the keys enable, optionally adding a layer of ceremony in front where you tap “approve”. I’m looking at the alert that is shown there and I don’t see anything that makes me feel like it allows for an informed choice at the time of it popping up. So then, what’s the benefit?


Replies

fractorial • today at 3:35 AM

As much as I wanted to say you’re wrong, you’re right. After reading TFA, the security boundary is not sound.

Wanting agents to act like you is wrong. You need to own that trust boundary. Build whatever tooling satisfies the contract that agents should have a “not”+<you> (or <you>+”-agent”) identity, and you actuate across that boundary explicitly.

For example, I have a second agent GitHub account that points at my human one. That allows me to write a trusted proxy that ACLs its identity tightly.

It cannot write to public repos ever. In the worst possible case, it externalizes to a private repo’s issue tracker. (Still has never happened in ~4 months)

Once you have this, you can let agents run free. But, it isn’t trivial to set up. Moreover, people don’t want to “do the work.”

All this assumes you abide by “never run untrusted agents on trusted hardware.”

➕ show 2 replies
binsquare • today at 4:25 AM

Basically these designs are meant to protect the key from leaking i.e. if agent holds key, prompt injections can happen.

If agent never holds the key, then the risk profile changes.

But you're right that it's a different problem to what access the key has and that's a different problem usually solved by having narrower keys or etc.

disclaimer: I work on smolvm which does this at the networking layer and argued with myself on this too.

➕ show 2 replies
recursivedoubts • today at 4:05 AM

I'm trying to address this w/ clank.talk: a self-discoverable scripting language for agents that replaces bash with a controlled sandbox environment and strives to be easy for humans to read:

https://clank.talk

I'm designing this for the student AI infrastructure here at Montana State, to avoid rolling out the current wild-west of local agents to our student body.

➕ show 2 replies
gunalx • today at 8:34 AM

On the ceremony. Maybe we should create a jev like model finetuned to know what is considered safe and not to only prompt the more unknown cases

rao-v • today at 7:53 AM

It's more about ensuring that the keys have some modicum of responsible control. If you give naked keys to Claude in a chat session and use something like atuin threads in 6 months to sync agent sessions across machines you might have put your keys in a a few dozen files without realizing it.

In an ideal world, the key you give Claude isn't useful for more than X amount of time, and ideally not against the true endpoint at all.

➕ show 1 reply
jarym • today at 7:53 AM

I keep seeing these various tools and asking myself the same question over and over.

Security professionals have been muzzled around AI usage and people that don’t really seem to know much about it are now writing the most ill conceived things about how to secure it.

antoniomika • today at 3:52 AM

Truthfully, I tend to agree with you. I built lend mainly for the fact that I like ssh tools a lot (feel free to check my other projects) and have always wanted a way to run local commands without having to setup reverse ssh when I don't need to run sshd on my laptop.

For example, I store k8s credentials in 1pass and the cluster is only accessible via the network on my remote machine. I can grab the credentials from my laptop for the work I want to do on the remote, and never have to install 1pass on the remote machine.

Primary use case for lend wasn't agents when I started the project. It just was natural to add support for it after the fact.

➕ show 1 reply
krupan • today at 3:11 AM

This is actually a big difference between giving someone you don't trust your keys and unlocking the door for them when they ask.

➕ show 1 reply
agentdev001 • today at 3:29 AM

> "when basically giving their AI direct access to what the keys enable"

Well, ideally, you would be giving the model direct access to a subset of what a given key enables- if fine grained access control for generated keys isnt available.

cj00 • today at 3:03 AM

Not having the credentials make it into the chat transcript for one.

➕ show 1 reply
protocolture • today at 6:34 AM

>I just don’t think I agree with these designs at all. Everyone seems to be super laser focused on “not allowing their AI to have keys” when basically giving their AI direct access to what the keys enable, optionally adding a layer of ceremony in front where you tap “approve”.

Yeah just follow least privilege. Give them only what they need/you trust them with.

petesergeant • today at 6:22 AM

I wrote a service for just that, which I should probably open-source. It basically wrapped permissioned APIs, and you would set fine-grained controls (eg you can email people at this domain without approval, but you need per-email approval for anything else).

Orygn • today at 6:19 AM

[flagged]

nghiemphucminh7 • today at 4:03 AM

[flagged]