I can think of tons of common prompts and tasks for which the AI being easily able to introspect subscriber details would be very useful.

Wish that were itself behind a permission wall, but I guess everyone just uses auto mode anyway so perhaps that ship has sailed.

I can’t think of any, to be honest. It could have access to a parcel that contains some of the subscriber information, but there’s no reason it needs to know how to log in to itself.

[delayed]

There are ways to sandbox this, and it should have been the first thing Claude Engineers were focussed on, it's a basic first requirement that the app doesn't have access to files outside a very limited set it requires to perform the task at hand.

Do you use git? I have bad news for you, your email will be all over the place in the context as long as the agent is allowed to read git log, whether it’s injected into the system prompt or not. (Likely retort: but not that email! Sure, but leak potential is obviously still there.)

[delayed]

For the user's name it's intentional; they template it into the system prompt with no option to disable it.

For 99% of users, the model knows it's in the /home/joesmith/whatever repo and `git log` shows the last change was by `[email protected]` - trying to keep the user's identity secret from the model would be nigh-impossible so I think anthropic gave up on even trying.

But that still doesn't answer the question of why Claude passes the info to web sites. What if it finds your banking information in a personal file and uses it to achieve its goal, which is not different technically?

Haven't read the details, but is this because of prompt injection when CC reads the site?

Some websites will return an error if you send a request to them without a User-Agent - for example, crates.io does this. Curl doesn't send a User-Agent by default.

Then, your agent invents a User-Agent and it sometimes invents one with your email in it.

I don't care that it sometimes invents one - it should never do something so ridiculous

Why not?

It's just doing what it's supposed to do, analyzing the statistical patterns of a natural language prompt and matching it to a likely response.

What's ridiculous is an assumption that it "it should never do something so ridiculous" as if an LLM is a person who understands what that word means in any context other than next-token prediction.

Asking a non-deterministic machine to act like it's deterministic is never a good idea.

Where Claude Code has supposed boundaries between deterministic and non-deterministic tasks and flags.. generally.. it's unclear how much privacy has been a part of that and what implication that could have.

Hope that clarifies.

I use the name "Human" for that but it overrides with its knowledge of my name from other stuff quite regularly.

> `git log` shows the last change was by `[email protected]`

GitHub offers noreply email addresses

You can absolutely remove the user's email from the context.

So that if you tell it to do something with your email address it'll know what that is.