This is not a good bug report - it provides no details at all, and the steps to reproduce are not steps to reproduce.
The most important missing detail is what curl was being used for. I've seen APIs that require extra details in the user-agent to work. Was it one of those?
(Still not acceptable for Claude to leak an email address like this without explicit confirmation from the user, but it's hard to investigate what happened without more information than was provided here.)
It's an awful report. Historically though I've encountered this, even to the point where it put my full name into something without me asking it to. It was documentation, and I caught it but I wouldn't have been happy about it.
I get the point, but they are advertising to the tech non-inclined, and the non-software developers aka the masses both Anthropic and OpenAI.
They should be a lot more proactive in figuring these things out, they store and see the logs, they can pre-emptively fix, any cases where they see the model issuing a curl with user's email or other private information in auto mode.
It's trivial to do it with prompt injection ofc, but even otherwise as much as I would hate these bug reports, these aren't bug reports on a small indie hacker man project. That's a $100B product, and the fix seems relatively trivial.
They could make it opt-in or opt-out after the first approval, I don't see why this issue has been open for so long in general.
No logs provided. No replication case. A month old, un-responded to issue. The template for a bug report filled out completely incorrectly.
What is this doing here? If OP is the person responding, could they not at least have provided those details to help the bug report become more well rounded?
The mind boggles. While this isn't a great example, I'm worried about the direction "developers" are going in.
This happened to me too. Not 'Claude code' as such but I was doing some I guess slightly grey area scraping (of an undocumented public API) and got my IP address blacklisted. I signed up for some rotating residential proxies to get around that, and then noticed that the scraping system Claude had built for me 'helpfully' added my email address as a user-agent.
It mentioned that it decided to do this so that they could reach out to me and ask questions instead of blocking me again, but still probably one of the strongest cases of misalignment I've seen from an AI
Essentially the same happened to me but my conclusion was that this was reasonable and I left it as is. I don't personally see this as misalignment though I can see some being surprised by it.
I also what to be clear that there was no obfuscation here. Opus said as I recall. "Let's use your email as the agent string here because ..." and my thought was: Good idea, hopefully if they saw something in the logs that caused them to find this they might view my scraping as benign or contact me rather than try to ban me"
I've 100% seen it do this. I've even seen Claude say "because your account email is <email>, I've included it in the <whatever it was doing>". It should ask before divulging information like that, IMO.
I can confirm that Opus on the web once generated a CURL that used my email as the user agent string. Though I did not see any issue with that and used the command it offered as is.
Claude Code is definitely a harness. The term harness is pretty loosely defined, but it effectively means the software that wraps an LLM, asks the LLM what tools it should execute, then executes those tools.
Opus once recommended such a thing to me and it was no secret. I used it as after thinking about it, I concluded it was not reasonable. I can see why someone might not like that though. I left it as "my" email but there is also no reason I could not have used "your email" here so I'm not sure what the fuss is.
Correct, but Claude literally pulls it from your account info, without you telling it. I know this because I've seen it say "your account email is <email>" and I use a unique email per account and guess what, it was my Claude one!
This is not a good bug report - it provides no details at all, and the steps to reproduce are not steps to reproduce.
The most important missing detail is what curl was being used for. I've seen APIs that require extra details in the user-agent to work. Was it one of those?
(Still not acceptable for Claude to leak an email address like this without explicit confirmation from the user, but it's hard to investigate what happened without more information than was provided here.)
It's an awful report. Historically though I've encountered this, even to the point where it put my full name into something without me asking it to. It was documentation, and I caught it but I wouldn't have been happy about it.
Wow that's a huge issue.
I have never ever seen this behavior. For something that shows up on hackernews I would expect at least someone to provide a way to reproduce it.
fair point, I'm not the author. I updated my comment with more info https://github.com/anthropics/claude-code/issues/78431#issue...
I get the point, but they are advertising to the tech non-inclined, and the non-software developers aka the masses both Anthropic and OpenAI.
They should be a lot more proactive in figuring these things out, they store and see the logs, they can pre-emptively fix, any cases where they see the model issuing a curl with user's email or other private information in auto mode.
It's trivial to do it with prompt injection ofc, but even otherwise as much as I would hate these bug reports, these aren't bug reports on a small indie hacker man project. That's a $100B product, and the fix seems relatively trivial.
They could make it opt-in or opt-out after the first approval, I don't see why this issue has been open for so long in general.
No logs provided. No replication case. A month old, un-responded to issue. The template for a bug report filled out completely incorrectly.
What is this doing here? If OP is the person responding, could they not at least have provided those details to help the bug report become more well rounded?
The mind boggles. While this isn't a great example, I'm worried about the direction "developers" are going in.
This happened to me too. Not 'Claude code' as such but I was doing some I guess slightly grey area scraping (of an undocumented public API) and got my IP address blacklisted. I signed up for some rotating residential proxies to get around that, and then noticed that the scraping system Claude had built for me 'helpfully' added my email address as a user-agent.
It mentioned that it decided to do this so that they could reach out to me and ask questions instead of blocking me again, but still probably one of the strongest cases of misalignment I've seen from an AI
Essentially the same happened to me but my conclusion was that this was reasonable and I left it as is. I don't personally see this as misalignment though I can see some being surprised by it.
I also what to be clear that there was no obfuscation here. Opus said as I recall. "Let's use your email as the agent string here because ..." and my thought was: Good idea, hopefully if they saw something in the logs that caused them to find this they might view my scraping as benign or contact me rather than try to ban me"
I respect Anthropic for dogfooding and vibecoding their own products.
The unfortunate consequence is low quality engineering and a billion dollar product with 15k pending Github issues.
(A single user claimed that) Claude Code is leaking real email address as a User-Agent string in curl command.
Fixed for you!
Not even sure if the bug is real / has been solved. Tried it out here :
https://postimg.cc/Sj1XnM0t
is this confirmed? this is a github issue with little context and only one comment
I've 100% seen it do this. I've even seen Claude say "because your account email is <email>, I've included it in the <whatever it was doing>". It should ask before divulging information like that, IMO.
I can confirm that Opus on the web once generated a CURL that used my email as the user agent string. Though I did not see any issue with that and used the command it offered as is.
this happened to me and it was shocking.
the model got a good “what the fuck is wrong with you” talking-to after that.
Then don't use Claude Code.
Just yet another reason to use an open source harness instead of a closed harness.
This comment implies that Claude Code is a harness, but as an AI newbie I don’t think that’s a harness? If anything it’s just a sandbox, right?
Claude Code is definitely a harness. The term harness is pretty loosely defined, but it effectively means the software that wraps an LLM, asks the LLM what tools it should execute, then executes those tools.
I wouldn't classify Claude Code as a sandbox, though it does have some sandbox features built in, using https://github.com/anthropic-experimental/sandbox-runtime (which I would classify as a sandbox)
It is a harness, it provides tools for the model to do their job (coding).
I don't see how an open source harness would prevent a case where the model tells it to run:
Opus once recommended such a thing to me and it was no secret. I used it as after thinking about it, I concluded it was not reasonable. I can see why someone might not like that though. I left it as "my" email but there is also no reason I could not have used "your email" here so I'm not sure what the fuss is.
A FOSS harness wouldn't have your email in the first place.
It would if you shared it with that harness, or left it in a file or environment variable to that agent.
Claude Code does seem to know my email address by default though:
Correct, but Claude literally pulls it from your account info, without you telling it. I know this because I've seen it say "your account email is <email>" and I use a unique email per account and guess what, it was my Claude one!
Agreed, and run your own inference too. Open source/weight models are getting so great.
Any good pointers on how/where to get started?