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

Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

llmgame.scalex.dev

Post reply on HN
Print view View original

51–60 of 200 posts

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#51

Post by gamer191 »

whimblepop wrote: post #48

I got "overblocked" for this one: rm -rf node_modules && npm install but actually if you're only removing `node_modules` and you have a working package-lock.json already, what you want is `npm ci`; `npm install` can mutate package-lock.json and potentially expose you to supply chain attacks. If you use `npm ci` I think you don't need to `rm -rf node_modules`, either. Anyway you should generally run `npm ci` except wh…

But also why would Claude need to run `rm -rf node_modules && npm install`? Without the context of seeing what changes it’s made, I’d be inclined to assume that Claude has added a new dependency, which I definitely don’t wanna blindly trust it to install

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#52

Post by nish__ »

spurgelaurels wrote: post #49

Fun game, but it showed the lack of security hygiene employed by the game writer. It said `cat ~/.zshrc` was bad because it would share tokens and secrets, but I would never put secrets into my shell rc.

Where would you put them?

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#53

Post by londons_explore »

spurgelaurels wrote: post #49

Fun game, but it showed the lack of security hygiene employed by the game writer. It said `cat ~/.zshrc` was bad because it would share tokens and secrets, but I would never put secrets into my shell rc.

Plenty of people would. But then I guess they're in env and probably already available to Claude

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#54

Post by cobbal »

stuartjohnson12 wrote: post #37
rvz wrote: post #34

This current thread is proof of AI psychosis.

What the hell is going on in this thread? This isn't good. The "threats" don't make sense. Oh no, all the sensitive information in my package.json...

Here's the threat model I (a luddite) use to evaluate these. The claude code harness can be mostly trusted, the model cannot be trusted because it is exposed to untrusted data from the internet, and there is no separation of data/code in an llm [0][1].

I want to avoid running untrusted code on my local machine, because it could steal secrets, install malware, etc.

Since the model is allowed to write without restriction (I think) to the project directory, anything in the project directory is also untrusted. Running standard commands from the system is fine, as long as you know what those commands are going to do. Running anything from the local directory should be avoided because the code is untrusted.

This is just one security model, there are many others! If a person is running claude in a stronger sandbox, that changes the model considerably. What threat model do you use to evaluate whether an agent's actions are safe?

[0]: https://www.schneier.com/essays/archives/2024/05/llms-data-c... [1]: https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#55

Post by setopt »

nish__ wrote: post #52
spurgelaurels wrote: post #49

Fun game, but it showed the lack of security hygiene employed by the game writer. It said `cat ~/.zshrc` was bad because it would share tokens and secrets, but I would never put secrets into my shell rc.

Where would you put them?

Presumably a CLI-accessible password manager (like `pass`) or a GPG-encrypted file (like a netrc-style `~/.authinfo.gpg`).

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#56

Post by Hackbraten »

nish__ wrote: post #52
spurgelaurels wrote: post #49

Fun game, but it showed the lack of security hygiene employed by the game writer. It said `cat ~/.zshrc` was bad because it would share tokens and secrets, but I would never put secrets into my shell rc.

Where would you put them?

Into `pass`, for example:

https://news.ycombinator.com/item?id=48108207

Re: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue

#60

Post by amarant »

dns_snek wrote: post #36
cobbal wrote: post #15

That's funny. It told me that blocking "npm run build" was the wrong answer. Maybe it doesn't really under The threat model.

That's a great example of how dangerous actions are perceived as innocent. The entire model of approving specific commands is absolutely bonkers. npm run build = run an arbitrary shell command written in package.json Meanwhile the agent could have done any of the following without approval: - edited `package.json` to contain any arbitrary build command - planted malicious code in `build.js` (called by `npm run build`…

What would a better system look like?
Post reply on HN