Show HN: Stroq – a local audit of what your coding agent did and why

Posted by agybay_07 1 day ago

Comments

Comment by philips 17 hours ago

I have been working on putting agents into full gVisor isolation with a default deny egress proxy that includes secret injections. When an agent tries to connect outbound, by default it suspends the gVisor, holds the proxy connection open, and lets the user choose.

I am adding external judges now. But, there is a hypervisor key you press to deny/allow hosts without switching terminals.

I just can't get behind relying on the harness tool boundry to protect me.

Comment by hedgehog 15 hours ago

Are putting the agent core and the workspace in separate containers? I do a limited version of that to prevent runaway tests etc from stopping jobs but making it a stronger boundary seems like a good idea.

Comment by philips 14 hours ago

Yes. Very alpha. https://hshrun.org

Comment by sebmellen 14 hours ago

Would love to collaborate with you on this since we’re building something analogous internally.

Comment by maven29 22 hours ago

You could cover a lot more adversarial scenarios with an ebpf backend. It needs linux, but with all the patches going around, you should be doing all your dev in a VM anyway. https://eunomia.dev/agentsight/

Comment by agybay_07 22 hours ago

[dead]

Comment by cucoo 5 hours ago

This is cool. I am working on a similar project but to remove PII and other sensitive info while talking with AI providers in an transparent manner. I started this because I am not comfortable sharing all this info with AI.

Comment by agybay_07 5 hours ago

its great that you're interested in this topic, good luck)

Comment by cucoo 5 hours ago

same

Comment by agybay_07 1 day ago

I've built project that helps to protect your computer from dangerous commands that your ai agent might execute. Have you noticed how often dont even check what our agents are actually running? Thats why I created Stroq. Try it locally npx @stroq/cli

Comment by embedding-shape 23 hours ago

> helps to protect your computer from dangerous commands that your ai agent might execute

How does "a local audit of what your coding agent did and why" help prevent dangerous commands? Sounds like your solution comes too late, innit? Sure, I can see that at 16:48 the agent ran "rm -rf --no-preserve-root" but if it already executed it on my personal computer, isn't it too late then?

Personally, I think this solves the wrong problem. If you're one stray "rm" away from letting the agent delete stuff on your personal computer, you're running the agent harness the wrong way. At least give it its own user, ideally limit what paths/network it can use, but don't rely on "auditing" to prevent dangerous commands, it'll bite you in the future.

Comment by arnarbi 22 hours ago

You are correct, but it's generally very hard to come up with good access control policies up front. Also, as you grant more access the system tends to become over-permissioned over time, and often you don't really find out until so wrong that it hurts. The ability to audit is necessary to maintain good policies. It allows you to discover gaps in your policy even when things didn't break terribly.

Comment by agybay_07 22 hours ago

You’re right the command from my comment only generates a report and doesn’t actually prevent anything. stroq init sets up hooks that prompt for confirmation before a dangerous command is executed—but that’s a filter, not a sandbox

Comment by brkomir 21 hours ago

I have received two pre-interview repos from recruiters on LinkedIn (NK hackers targeting crypto people), and both would be hard cases for this. Almost all offers there in DMs are now fake recruiters, and it's not trivial to figure out if the account is fake.

One had an eval() hidden inside a controller function named getCookie(), running whatever a remote server sent back. npm start, npm build and npm test all triggered it. Cursor didn't catch it when I asked "is this repo safe to run?" and then told it to check all dependencies.

Other one came as a bunch of Solidity files in a zip file with an issue to resolve as the interview task, nothing suspicious at first sight. However, that zip carried the whole .git folder, hooks included, which a git clone never copies, and the folder is hidden by default in Finder. Of course, there was a hook that fires on any commit or push, again eval() on some remote address.

In both cases the agent only runs npm test or git commit. Would Stroq see anything in these situations?

Comment by agybay_07 20 hours ago

to be honest, in the first scenario, the hook will only detect 'nom test' command itself. in the second scenario 'stroq inspect' will identify the hook before the folder is opened and issue a warning. thanks for these examples :) I'll use them to improve product

Comment by brkomir 4 hours ago

[dead]

Comment by mariusziskra 3 hours ago

[flagged]

Comment by agybay_07 23 hours ago

[flagged]

Comment by chanux 10 hours ago

Could this be used with Agent Safe house? https://agent-safehouse.dev/

Comment by lhk931122 14 hours ago

Doing it with a high-performance LLM would be best, but I think the token and time cost would be big, and just doing it code-based seems like it could work to some extent. But later, if LLM alignment gets good, it might not even be needed.

Comment by agybay_07 13 hours ago

Yes, the rules dont catch everything but since this is an open-source project, anyone can add new rules, and I'll be looking for new approaches. as for the llm, it reads the same text as the agent, so it can be fooled as well)

Comment by lhk931122 13 hours ago

Of course, I do think it's really great in terms of cost. And since it's open source, it also has the advantage of being customizable.

Comment by bill10 12 hours ago

Interesting. How does it know: rule based, small model, or LLM? Anyway, like the mascot

Comment by agybay_07 12 hours ago

Thanks, the owl's name is Hoo) Stroq reads sessions logs and command text directly from the computer. There are no LLM models involved

Comment by emscb 16 hours ago

From the README, matching is text-level and nothing is sent out. So it seems to judge with rules, not an LLM. Is that right?

Comment by agybay_07 14 hours ago

yes

Comment by Krishansubudhi 11 hours ago

Like the owl. Add citations too.

Comment by agybay_07 11 hours ago

Thank you. What do you mean by 'citations'? Each item has a 'Stroq show' feature that displays the basis for it

Comment by hmokiguess 1 day ago

feature suggestion:

background daemon that continuously scans and alerts in a menubar app when a positive match is found

clicking the menubar app shows the offending entry, clicking the entry lets you redact, delete, repair, mark as false positive, etc.

Comment by agybay_07 1 day ago

Thanks) good idea

Comment by Krishansubudhi 11 hours ago

Is it fully programmatic ?

Comment by agybay_07 11 hours ago

Everything is performed programmatically, without using a model

Comment by sebion7125 17 hours ago

I'm wondering if that could be part of a prompt injection warn system in the future. Did I get it right, that it does not need an LLM to evaluate sessions?