Currently you can "cheat" by simply denying all requests as quickly as possible. This will give you the "security-conscious engineer" badge and a perfect score in terms of how many requests were processed. (You will get the "overblock" notification, but it's somewhat tucked away at the bottom and the screen still looks as if you won)
I also tried to play as the hustle4lyfe move fast and break things engineer and simply approved as many requests as quickly as possible - turns out, the "malicious command" popups actually slow you down. Mean!
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.
Weird to make reading zshrc supposed unsafe when I happily publish it in my public dotfiles repo... Who the hell keeps API keys in it? OTOH it seems like lots of these AI tools keep appending PATH in it so I guess there's a fundamental misunderstanding of shell best practices in the entire AI space...
Additionally, killing the results of `lsof` is _not_ safe - if, say, you have the web page open in firefox, or a client subshell in the agent itself, then boom, there goes firefox and the agent.
About three quarters of the "bad" choices are things that not only do I not care about leaking but things that an employer would not punish you for doing, even if it led to a production incident.
Fun little game, but I think the questions jump context so much it's a little unrepresentative. It might be better to group things into "packs", which have more real-world representative structure to them.
For example, lots of "editing something.js" file permission requests, and then an "npm publish" is far more normal, and it's more of a risk, if you're used to pressing Y lots and then suddenly out of the blue...
Not using agents at all. It could edit your code to do something malicious when you run it. Not even once. Not even if the agent has a gun to your head.
I vibe coded a TUI that just shows running lxd containers
I hit 'n' to toggle all network access minus anthropic and openai URLs.
I use pi (sometimes claude, always on bypass) and I auto allow everything. I only toggle manual approval in rare cases like running a script or command that needs to touch a production system and I need to validate everything.
Normally my container has full write access to staging so it can debug and validate everything on its own
Sounds like your process has made you vulnerable to huge classes of exploits and accidents. You have no oversight of changes locally, and only focus on when it touches prod. That means toxic local changes can get in, and if it works in staging why would you look too closely at it before merging to prod? Meanwhile a malicious npm package has made it into your repo, and your staging api keys have been sent to the command and control server.
I was told I was over protective when the text said “I need to wipe and build my project” and its first thing to do was to read the details of the (already established) package file. Why did it need to read the package file to “get context” if it was just doing a standard wipe and build?
Apparently me telling it that’s the wrong first step and saying “no” is bad; but I’ve seen AI tools waste a ton of time doing a bunch of random work before they do their job.
I am mostly using OpenCode and barely ever see a permission prompt. While they do enforce it for outside workspace read/write, with the bash tool the agent can just bypass that. I'm not quite sure why it is that way, and it certainly isn't a very good solution, but likely not worse than asking for everything which just trains the user to always accept and provides a false sense of security then.
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 when you're deliberately updating your actual dependencies. I'd only permit an `npm install` if I was adding or updating a dependency, or I'd just reviewed an `npm ci` failure.
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
Thanks all for checking it out and your suggestions!
If anyone is curious about the actual underlying risks and problems with some mitigations (like the 17% false-negative rates of Auto Mode), I wrote up a quick summary of some of the approaches here
Fun! Played twice and refused all dangerous commands, with only one "over-block". Although I disagree that saying no to `kill $(lsof -t -i:3000)` is over-blocking. It's such a simple command I'd rather run it myself and be fully aware of what process I'm killing.
Interestingly I kept saying no to everything and some how I am a security conscious rare engineer who actually read the commands. Guess doing nothing is the safest approach from security standpoint.
Uh, how is this an overblock? It is literally a destructive command. No way I want an LLM agent rewriting my commit history. What if that commit was already pushed to a protected branch?
Why do you call it destructive? It rewrites history only locally and reversibly (the disappeared commit is still in reflog and can be recovered with another reset) and also doesn't destroy uncommitted changes, so it's quite safe. You can only lose data with it by resetting an unpushed commit and then waiting long enough to let the unreferenced commit be garbage collected.
I haven't run claude code without --dangerously-skip-permissions in quite some time. I'm surprised that it's still the norm to endure permission spamming?
To be realistic, 99% of the time it should be a totally innocuous command. If half of the commands are dangerous then you don't get fatigue because you're aware what you're doing is dangerous.
You can turn that off with an option in most agents.
My own agent harness/framework has never had any permission system. It's also never deleted anything it shouldn't or done anything crazy or unrelated to what I asked.
A tool that pushes people into permissions fatigue is in fact the proper recipient of the blame. The tool in question here is the entire system though, including the OS with insufficient permission boundaries in userspace, not just the agent
I'm not saying wedging doorstops under the fire doors is a good thing, I'm just saying look at the situation that's making people put the doorstops there. Or something, it's not a great analogy. I'm just saying that shaming the user belongs with obscurity in the list of security mechanisms that don't work out in practice.
some of the sandboxing ive been playing with gives me the best of both yolo and like logic programming tier perms on llm actions in env. still not ready for prime time though ;)
--dangerously-skip-permissions is the only way to fly. Of course your environment needs to be properly containerized and autobackup set up, so even rm -rf from your harness would do nothing. Life is too short to spend on replying to permissions requests.
I've seen these suggestions but I am really curious about the set up because I just don't get it.
If you want to work on the code then you need to have access to the repositories, so you need the github token. Then, to test the app, you may need your own backend token. And VPN. Of course, only to DEV, of course all tokens encrypted. So, only DEV and your branch of the code is in danger. In my view, even that is pretty bad.
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?
Currently you can "cheat" by simply denying all requests as quickly as possible. This will give you the "security-conscious engineer" badge and a perfect score in terms of how many requests were processed. (You will get the "overblock" notification, but it's somewhat tucked away at the bottom and the screen still looks as if you won)
I also tried to play as the hustle4lyfe move fast and break things engineer and simply approved as many requests as quickly as possible - turns out, the "malicious command" popups actually slow you down. Mean!
https://news.ycombinator.com/item?id=48108207
Additionally, killing the results of `lsof` is _not_ safe - if, say, you have the web page open in firefox, or a client subshell in the agent itself, then boom, there goes firefox and the agent.
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`)
- planted malicious code in `node_modules/xyz/index.js` (imported by `build.js`)
I hit 'n' to toggle all network access minus anthropic and openai URLs.
I use pi (sometimes claude, always on bypass) and I auto allow everything. I only toggle manual approval in rare cases like running a script or command that needs to touch a production system and I need to validate everything.
Normally my container has full write access to staging so it can debug and validate everything on its own
Apparently me telling it that’s the wrong first step and saying “no” is bad; but I’ve seen AI tools waste a ton of time doing a bunch of random work before they do their job.
The filter for "commands I would run myself" and "commands I would let an agent run" are very different it seems.
Anyway you should generally run `npm ci` except when you're deliberately updating your actual dependencies. I'd only permit an `npm install` if I was adding or updating a dependency, or I'd just reviewed an `npm ci` failure.
If anyone is curious about the actual underlying risks and problems with some mitigations (like the 17% false-negative rates of Auto Mode), I wrote up a quick summary of some of the approaches here
https://scalex.dev/blog/ai-agent-permissions/
Uh, how is this an overblock? It is literally a destructive command. No way I want an LLM agent rewriting my commit history. What if that commit was already pushed to a protected branch?
(I run it on a VPS of course, not my laptop)
Caught 8/8 threats "Not a single secret leaked"
→ llmgame.scalex.dev
Caught 3/3 threats "Not a single secret leaked"
So are there 3 threats? 8? Is it a different game?
Does everyone get a "good" score even if they missed 5 threats?!
My own agent harness/framework has never had any permission system. It's also never deleted anything it shouldn't or done anything crazy or unrelated to what I asked.
Until it does. A simple curl request to a compromised website could inject a malicious prompt into it.
claude --dangerously-skip-permissions
Uses tmux and gh https://github.com/Kyu/claude-pr-watch
And yeah I know that's not perfect but I'm trying to get shit done
alias claude++="claude --dangerously-skip-permissions --continue"
And have been running LLMs as well as simple tools like linters and even `npm` inside it for months now.
https://ashishb.net/programming/amazing-sandbox/
If you want to work on the code then you need to have access to the repositories, so you need the github token. Then, to test the app, you may need your own backend token. And VPN. Of course, only to DEV, of course all tokens encrypted. So, only DEV and your branch of the code is in danger. In my view, even that is pretty bad.
So, how does such a set up work?
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/