[SpicyLemonZest]

Who knows whether permissions would prevent this? Anthropic's documentation on permissions (https://code.claude.com/docs/en/permissions) does not describe how permissions are enforced; a slightly uncharitable reading of "How permissions interact with sandboxing" suggests that they are not really enforced and any prompt injection can circumvent them.

[jatora]

With hooks you can enforce permissions much more concretely.

[SpicyLemonZest]

Perhaps they're more functional. Hooks are configured in the same settings file, which makes me pretty skeptical in the absence of explicit confirmation that they represent a stronger security boundary. (But of course, this is a fundamental challenge with LLM agent security - if you're using a well-aligned model that doesn't want to be prompt injected, how do you go about auditing something like this?)

[jatora]

ya they definitely cant stop everything. nothing can be stopped if you allow python honestly, but hooks are guaranteed to fire on every tool use so you can bake in explicit rejections for different patterns based on regex which can catch a lot of nonsense