Hacker News Reader

Comment by VTimofeenko | Hacker News Reader

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).

View on HN

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?".

That's a distinction without a difference, in the end you still have an arbitrary bash command that you have to validate.

And it is simply easier to whitelist directories than individual commands. Unix utilities weren't created with fine-grained capabilities and permissions in mind. Wherever you add a new script or utility to a whitelist, you have to actively think whether any new combination may lead to privileges escalation or unintended effects.

> That's a distinction without a difference, in the end you still have an arbitrary bash command that you have to validate.

No, you don't. You have a command generated by auditable, conventional code (in the agent wrapper) rather than by a neural network.

That command will have to take some input from neural network though? And we're back in Bobby Tables scenario

No, that argument makes no sense. SQL injection doesn't happen because of where the input comes from; it happens because of how the input is handled. We can avoid Bobby Tables scenarios while receiving input that influences SQL queries from humans, never mind neural networks. We do it by controlling the system that transforms the input into a query (e.g. by using properly parameterized queries).

Right, in DBs it's proper param binding + prepared statements.

I see what you're saying, makes sense.

FWIW there is (in analytics) also RBAC layer, like "BI tool acting on behalf of user X shall never make edits to tables Y and Z"

Reply on news.ycombinator.com