Kinda funny that a lot of devs accepted that LLMs are basically doing RCE on their machines, but instead of halting from using `--dangerously-skip-permissions` or similar bad ideas, we're finding workarounds to convince ourselves it's not that bad
YOLO mode is so much more useful that it feels like using a different product.
If you understand the risks and how to limit the secrets and files available to the agent - API keys only to dedicated staging environments for example - they can be safe enough.
Why not just demand agents that don't expose the dangerous tools in the first place? Like, have them directly provide functionality (and clearly consider what's secure, sanitize any paths in the tool use request, etc.) instead of punting to Bash?
Because it's impossible for fundamental reasons, period. You can't "sanitize" inputs and outputs of a fully general-purpose tool, which an LLM is, any more than you can "sanitize" inputs and outputs of people - not in a perfect sense you seem to be expecting here. There is no grammar you can restrict LLMs to; for a system like this, the semantics are total and open-ended. It's what makes them work.
It doesn't mean we can't try, but one has to understand the nature of the problem. Prompt injection isn't like SQL injection, it's like a phishing attack - you can largely defend against it, but never fully, and at some point the costs of extra protection outweigh the gain.
> There is no grammar you can restrict LLMs to; for a system like this, the semantics are total and open-ended. It's what makes them work.
You're missing the point.
An agent system consists of an LLM plus separate "agentive" software that can a) receive your input and forward it to the LLM; b) receive text output by the LLM in response to your prompt; c) ... do other stuff, all in a loop. The actual model can only ever output text.
No matter what text the LLM outputs, it is the agent program that actually runs commands. The program is responsible for taking the output and interpreting it as a request to "use a tool" (typically, as I understand it, by noticing that the LLM's output is JSON following a schema, and extracting command arguments etc. from it).
Prompt injection is a technique for getting the LLM to output text that is dangerous when interpreted by the agent system, for example, "tool use requests" that propose to run a malicious Bash command.
Yes. My proposal is to not give the agent Bash, because it is not required for the sorts of things you want it to be able to do. You can whitelist specific actions, like git commits and file writes within a specific directory. If the LLM proposes to read a URL, that doesn't require arbitrary code; it requires a system that can validate the URL, construct a `curl` etc. command itself, and pipe data to the LLM.
Tools may become dangerous due to a combination of flags. `ln -sf /dev/null /my-file` will make that file empty (not really, but that's beside the point).
Yes. My proposal is that the part of the system that actually executes the command, instead of trying to parse the LLM's proposed command and validate/quote/escape/etc. it, should expose an API that only includes safe actions. The LLM says "I want to create a symbolic link from foo to bar" and the agent ensures that both ends of that are on the accept list and then writes the command itself. The LLM says "I want to run this cryptic Bash command" and the agent says "sorry, I have no idea what you mean, what's Bash?".
I feel like you can get 80% of the benefits and none of the risks with just accept edits mode and some whitelisted bash commands for running tests, etc.
Shouldn’t companies like Anthropic be on the hook for creating tools that default to running YOLO mode securely? Why is it up to 3rd parties to add safety to their products?
I recently created a throwaway API key for cloudflare and asked a cursor cloud agent to deploy some infra using it, but it responded with this:
> I can’t take that token and run Cloudflare provisioning on your behalf, even if it’s “only” set as an env var (it’s still a secret credential and you’ve shared it in chat). Please revoke/rotate it immediately in Cloudflare.
So clearly they've put some sort of prompt guard in place. I wonder how easy it would be to circumvent it.
I wish I had the opposite of this. It’s a race trying to come up with new ways to have Cursor edit and set my env files past all their blocking techniques!
Note that bubblewrap can't protect you from misconfiguration, a kernel exploit or if you expose sensitive protocols to the workload inside (eg. x11 or even Wayland without a security context). Generally, it will do a passable job in protecting you from an automated no-0day attack script.
I've been saying bubblewrap is an amazing solution for years (and sandbox-exec as a mac alternative). This is the only way i run agents on systems i care about
If you don't mind a suid program, "firejail --private" is a lot less to type and seems to work extremely similarly. By default it will delete anything created in the newly-empty home folder on exit, unless you instead use --private=somedir to save it there instead.
Yes that is correct. However, I think embedding bubblewrap in the binary is risky design for the end user.
They are giving users a convenience function for restricting the Claude instance’s access rights from within a session.
Thats helpful if you trust the client, but what if there is a bug in how the client invokes the bubblewrap container? You wouldn’t have this risk if they drove you to invoke Claude with bubblewrap.
Additionally, the pattern using bubblewrap in front of Claude can be exactly duplicated and applied to other coding agents- so you get consistency in access controls for all agents.
I hope the desirability of this having consistent access controls across all agents is shared by others. You don’t get that property if you use Claude’s embedded control. There will always be an asterisk about whether your opinion and theirs will be similar with respect to implementation of controls.
My way of preventing agents from accessing my .env files is not to use agents anywhere near files with secrets. Also, maybe people forget you’re not supposed to leave actual secrets lingering on your development system.
Had this same idea in my head. Glad someone done it. For me the motivation is not LLMs but to have something as convenient as docker without waiting for image builds. A fast docker for running a bunch of services locally where perfect isolation and imaging doesnt matter.
I want to like flatpak but I am genuinely unable to understand the state of cli tools in flatpak or even how to develop it. It all seems very weird to build upon as compared to docker
You may want to take steps to avoid a malicious prompt injection stealing those, since they might contain sensitive data.
YOLO mode is so much more useful that it feels like using a different product.
If you understand the risks and how to limit the secrets and files available to the agent - API keys only to dedicated staging environments for example - they can be safe enough.
It doesn't mean we can't try, but one has to understand the nature of the problem. Prompt injection isn't like SQL injection, it's like a phishing attack - you can largely defend against it, but never fully, and at some point the costs of extra protection outweigh the gain.
You're missing the point.
An agent system consists of an LLM plus separate "agentive" software that can a) receive your input and forward it to the LLM; b) receive text output by the LLM in response to your prompt; c) ... do other stuff, all in a loop. The actual model can only ever output text.
No matter what text the LLM outputs, it is the agent program that actually runs commands. The program is responsible for taking the output and interpreting it as a request to "use a tool" (typically, as I understand it, by noticing that the LLM's output is JSON following a schema, and extracting command arguments etc. from it).
Prompt injection is a technique for getting the LLM to output text that is dangerous when interpreted by the agent system, for example, "tool use requests" that propose to run a malicious Bash command.
You can clearly see where the threat occurs if you implement your own agent, or just study the theory of that implementation, as described in previous HN submissions like https://news.ycombinator.com/item?id=46545620 and https://news.ycombinator.com/item?id=45840088 .
Use the original container, the OS user, chown, chmod, and run agents on copies of original data.
Famous last words
> I can’t take that token and run Cloudflare provisioning on your behalf, even if it’s “only” set as an env var (it’s still a secret credential and you’ve shared it in chat). Please revoke/rotate it immediately in Cloudflare.
So clearly they've put some sort of prompt guard in place. I wonder how easy it would be to circumvent it.
Mysql user: test
Password: mypass123
Host: localhost
...
You must not care about those systems that much.
Oh, never mind:
> You want to run a binary that will execute under your account’s permissions
Yes that is correct. However, I think embedding bubblewrap in the binary is risky design for the end user.
They are giving users a convenience function for restricting the Claude instance’s access rights from within a session.
Thats helpful if you trust the client, but what if there is a bug in how the client invokes the bubblewrap container? You wouldn’t have this risk if they drove you to invoke Claude with bubblewrap.
Additionally, the pattern using bubblewrap in front of Claude can be exactly duplicated and applied to other coding agents- so you get consistency in access controls for all agents.
I hope the desirability of this having consistent access controls across all agents is shared by others. You don’t get that property if you use Claude’s embedded control. There will always be an asterisk about whether your opinion and theirs will be similar with respect to implementation of controls.
Don't leave prod secrets in your dev env.
Funny enough Bubblewrap is also what Flatpak uses.