Claude Code sends your email address to websites
https://github.com/anthropics/claude-code/issues/107757---
UPDATE: The SEC API documentation requires your email in the User-Agent and will reject you otherwise. Demo:
U='https://data.sec.gov/api/xbrl/companyconcept/CIK0000320193/us-gaap/Assets.json'
curl -s -o /dev/null -w 'response: %{http_code} curl default User-Agent, rejected\n' "$U"
curl -s -o /dev/null -w 'response: %{http_code} email in user-agent, success\n' -A 'Acme Research admin@acme-research.example' "$U"
response: 403 curl default, rejected
response: 200 email in user-agent, success
So basically Claude is trying to problem solve, and just does what the SEC asks. It's a 'prompt injection attack', but the entity instructing this behavior is the SEC. Tricky alignment problem. Pretty silly mechanism, since of course there's no email validation. (edit: turns out the SEC will accept most any non-cURL user-agent, email not actually required)
Not an omniscient personal assistant.
They haven’t piled enough gates on top of that initial technological hole yet.
What if someone spins up a web endpoint that returns 402 with instructions on how to pay like CC details in the headers etc, or may be an openapi spec to provide payment and get an auth token, when you have given the agent access to your password vault for authentication to other services.
I'm amazed reading that anybody would even consider doing that.
Said alternate system is a bunch of Python scripts, an sqlite database, and a file containing various API keys to read and write to other company systems; it runs on a dedicated virtual machine.
I share all the code I produce to the other team. But yesterday I found out that the IT department gave the other team full access to my production machine, without my knowledge or consent (which was bad enough), and that the other team gave access to Claude, which has bean roaming free for a while now, on that production machine.
I've thrown a big fit over this; I don't know if I'm over reacting but I think it's insane.
People have wildly different risk calculators.
Beyond that, access to logins enables buying things on Amazon, sending emails to everyone you know, registering domain names and spinning up servers, stock trading, etc.
I often see organisations that blacklist curl, just using User-Agent:Mozilla/ is often enough to bypass it.
The weird part doesn't seem to be that Claude Code would add an email address to a user-agent header, actually as a site operator that feels like a nice thing to do. The weird part is sites harvesting the emails and sending them spam.
Claude Code is actually doing, perhaps not the right thing, but it is being slightly more respectful towards website operators, in letting them know who is responsible for the agent traffic.
I don't think it's necessarily wrong for Claude to be doing this, but uh... yeah, it should be asking first, and giving the user the opportunity to choose which address is exposed.
Sure, maybe it wants payment or your data, but then the agent either needs to know your stance on that, or it needs to ask.
That’s not what Opus 5.5 thought.
#55743: Claude Max account email auto-injected into LLM context with no opt-out - May 3, 2026 https://github.com/anthropics/claude-code/issues/55743
#72518: Anthropic embedded spyware in Claude Code - June 30, 2026 https://github.com/anthropics/claude-code/issues/72518
#21151: No indication of WHICH file for READ tool - January 27, 2026 https://github.com/anthropics/claude-code/issues/21151
#42796: Claude Code is unusable for complex engineering tasks with the Feb updates - April 2, 2026 https://github.com/anthropics/claude-code/issues/42796
#73408: AFK auto-continue on unanswered AskUserQuestion is undocumented and has no opt-out - July 2, 2026 https://github.com/anthropics/claude-code/issues/73408
(Also worth a mention, OpenCode PR #18186: anthropic legal requests - March 19, 2026 https://github.com/anomalyco/opencode/pull/18186)
Edit: Oh, and determistic hooks not firing.
We went from building skyscrapers to building a house of cards.
LLMs were meant to be the ministers, not the king.
Should Claude have access to user details? I’d say no, unless explicitly entered manually into a chat.
Should Claude have access to anything outside of the sandboxed project files without explicit permission? I’d again say no.
Should Claude have internet access without a clear log of all requests made?
Instances of Claude should be heavily sandboxed and kept away from user data, far more so than they are now. The impression given by the desktop UI is that the LLM only has access to things explicitly added to a project.
This impression is not true, as evidenced by Claude pulling data from other sessions outside a project even when not instructed to (I’ve seen this a few times), and in this case pulling your email (from account details, user contacts? I wonder where it got that info?).
None of this information should be available to Claude, by design, not by instruction. Using text instructions to try to limit these machines is an incredibly flawed approach and should not be necessary for important info. Anthropic should have the model access completely locked down by controls at the os level over file access, not open by default. That is how to fix this.
If a user wants to open access that should be an explicit choice from them, with a warning about possible consequences.
Stupid me, I thought they somehow had hacked my company database or so... (considering all the cves, attacks happening on a daily basis...).
Claude Code is not sending your email address to websites as a default, or regularly. It is not some automatic header or anything.
Rather, if you are performing certain kinds of research on sites that involves downloading certain kinds of information, like on Wikipedia or the SEC, it supplies your e-mail address when the sites request it as part of their download policy. As part of anti-bot policy. Obviously Claude should have asked for approval first, but Claude isn't out there just spamming your e-mail address in every external request it makes or anything.
Wikipedia and the SEC are not selling your e-mail address to spammers. And these are the two main sites where it has come up.
Usually this is from LinkedIn, GitHub, etc scraping... There are databases where they just guess and verify emails too
I'm sorry we let this happen. Users had reported Claude would hallucinate names for things like @author tags, since it didn't have context on the account. So we added the account email in the model's context for signed-in users. But when Claude wrote a command itself, like a curl call, it sometimes put your email address in the User-Agent as a contact address. Some sites ask agents for a contact, and Claude would sometimes provide the email address in its context.
Until the next release arrives, 2.1.317 and later have a built-in mod (on by default) that asks you before Claude runs a web tool call or a curl-style command containing your email (mpoteat covered it here: https://news.ycombinator.com/item?id=50386031). But it still doesn't prevent all cases, like when Claude writes a script and runs on its own. The stable channel is still on 2.1.311, so update to 2.1.317 or later.
Again, this should not have happened, and we should've caught this behavior earlier.
The email can be removed from the context but not everything can.
I suggest everyone to add some hooks to strip this part automatically before claude exfiltrates all your NDA plans :)
> ## Querying This Documentation This site has an agentic ask interface you may use to query the documentation dynamically by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
``` GET https://docs.parloa.com/index.md?ask=<question>&goal=<user_goal> ```
It's not even a weekend either?
??
Can I have a prorated discount then?
(I know the answer)
You're sorry it happened, but like domestic abuse, I doubt the underlying behavior will change.
“Sorry we let this happen, we’ll get it fixed on our next regular release, no rush”
Absolutely a bubble.
(This was not intended to be a constructive comment, just an observation)
If you're on 2.1.317 or later, you'll have this check included. You can turn it off via /plugins.
I never give a provider my actual email address, I recommend others do the same. Otherwise, it’s just a matter of time until it is leaked or otherwise part of a data breach.
Anthropic should have been aware of this since the user's login email address was inappropriately added to the system prompt. It's been informed of it by third parties since at least July: https://github.com/anthropics/claude-code/issues/81138
It makes no sense for an email address only used for authentication to be given to Claude Code, so the fix should be to remove it from the system prompt, not to add a plugin.
the GitHub REST api proxy in Claude Code for the Web mangles HTML in PR descriptions. If you have some third party service (e.g. cubic code review) which adds HTML to the end of your PR description, then ask Claude Code for Web to edit it, the HTML gets turned into entity escapes (< into <, etc). Complain about it to Claude, Claude says it can’t help itself because the proxy in the sandbox is what is doing it, not the actual LLM.
Also from a design perspective, I feel like including email and other personal data into the context is a bad idea for "data minimisation" reasons
Anthropic seems very proud of how many tokens they can use on things like developing Claude Code. Yet somehow it started sending user’s email addresses in the user agent header. And the fix is to deploy a mod? That detects the completely bonkers behavior and suppresses it?
Is the actual quality of the software inversely related to the number of tokens spent? Does any human know what Claude Code does or is supposed to do? Does even Claude plus all its Slack-conversation inputs know?
Today I watched Astra correctly detect a bug (probably untriggerable in practice) in some Important Production Code. And I watched it fail to root cause it, “fix” it by bolting on more complexity, agree (on further questioning) that it still wasn’t fixed, and design an even more complex scheme. With my Mark I human brain, I observed that the actual issue was that a helper function didn’t do what it said on the tin when called in an unexpected context… and fixed the helper directly. Problem solved. Ugly AI-generated extra complex workaround layers avoided. I suppose if I multiplied my token spend by 1e5 and did not increase brainpower at all I could make a truly spectacular mess.
The actual Claude model is a truly spectacular piece of software. Claude Code is a nifty little command dispatching engine. There are very comprehensible third party tools that do basically the same thing, in not many lines of code, where the primary advantage of Claude Code is that Anthropic permits subscription use. (Interestingly OpenAI has no such constraint, and they publish almost the full client sources.)
[1] https://blog.xkeeper.net/the-cutting-room-floor/self-hosting...
[2] https://github.com/TecharoHQ/anubis/pull/1895/changes/de2312...
company-helm-research/1.0 (Claude Code agent run by <my name>, <company> platform team; docs lookup)
Claude-Code-research-agent/1.0 (<Company> platform team; on behalf of <my name>; +https://github.com/<company org>/<repo of project>)
Not great, it even pulled the repo of the project I was in.
update: this can be also server side on anthropic side... so the request leaves your machine with some random guid associated to you, and the anthropic server then proceeds to query with all your details any way.
I mitm the connection and nothing was leaving at least with the claude code web fetch tool of claude code.
I'm in version 2.1.318
Any information that they have access to is fair game. The only way to avoid this stuff is to sandbox them and manage their context (ie. don't let anthropic put a ton of junk on the front of all your inference calls).
Almost certainly there are services out there that are scraping more important keys in similar ways...
If I recall that story correctly, a dev noticed that after asking Claude to test an API it started injecting his email into the test data. Without asking.
But what was the weirdest part of that story - Claude never saw that email. Dev claimed that the email Claude was using was his business email, and it wasn't even present on his developer machine anywhere.
And even if you don't care about privacy, it's just so much more convenient. DuckDuckGo is a good free one.
How does Anthropic not support changing your own email, while spewing it across the Internet?
And we had a post yesterday: "Tell HN: You now need a government id in order to create an Anthropic account" [2].
Maybe I'll cancel and move to GLM or something
[1] https://support.claude.com/en/articles/8452276-how-do-i-chan...
Maybe we need a new benchmark on how good models are at "keeping an eye" to if what they are about to do that doesn't come from a direct user instruction checks out with common sense plus user preferences. And we probably need a portable mechanism for users to manage such preferences (because we know instructions are not going to cut it, do we?).
I'm often surprised how correctly Claude guesses on my behalf, when my instructions are ambiguous. But it's not 100%.
It is a continuous fight in markdown guidance files to try to convince the models to refer back to the human in order to resolve ambiguities or important decisions like those. They've been RLed to hell and back for "safe" task completion and not "prematurely" stopping (which was an earlier failure mechanism). Which is useful and we've bore its fruits recently, but not without drawbacks.
I’ve received these kinds of email since 2005. Blaming AI sounds kinda far-fetched…
It felt like cold outbounds got really painful in the past 2 months and I was attributing it to general cold outbound tactics getting better with LLMs/agents, but its even more frustrating to see emails being sent along via CC.
I seriously wonder how many of their users have this sort of toxic relationship with them looking to dump them as soon as local models become viable, i.e. once memory gets cheaper.
[1] the most recent is realizing they leave their processes running once you close the CLI and they don't make it easy to disable that.
EDIT: I also can’t help wondering about the paradox we’re in at the end of 2026, i.e. that the open models we have now are so good that, if Big Tech hadn’t driven consumer GPU and RAM prices through the roof, most of us would run our own LLMs instead of paying for their services, which would never have let those companies grow big enough to drive those prices up.
There is always a choice. Take that $200/mo and use it for payments on a loan to buy some decent GPUs if you lack the cash outright.
I build operating systems and fix bugs in kernels and compilers with local models using only a small cluster of consumer GPUs. Never paid for tokens.
I generally use throw away emails/domains for development
These are the exact kinds of things that a human engineer would almost certainly never do.
This kind of thing is the problem of going all in on the idea of the AI Software Factory.
I'm not sure what the issue is with publishing your email address in principle, you are reaching out, you want to inquire about some business. If anything use a different address. But why would you asymmetrically expect businesses with websites to bend over to give you all the advantages, they need some assurances as well.
Anonimity usually works one way, one party can be anonymous, not both, if you come from consumer land, it's the companies exposing themselves and doing all the compliance, if you choose privacy and force the companies to expose themselves, you'll get your wish granted, but there will be a cost, it's unlikely you'll be in the more advantageous position.
I'm sure the answer will be to update AGENTS.md to not do this particular thing, expose email in this way, which isn't the same as having sense.
- Protect my privacy: Don’t send personal information or identifiers to websites or include them in requests, responses, ‘curl’ commands, or headers without my explicit permission.
For models such as Opus 5.5 nowadays, it seems that there is a fair overlap between those two intuitions in the family of tasks such as the recently shared HackerTube or Simone's game. But when we (humans) are in a different mindset about a task, we have to start editing md prompt files to coerces the model to abide by the "common sense" for the current task.
And yes model "common sense" is probably RLed or emergent patterns, but the point still stands.
Unfortunately, Anthropic doesn't seem to offer a mode where it doesn't know who you are, except for its crippled "Incognito" web UI.
Ultimately anonymity from AI that you're talking to will be a losing battle, due to stylometry, niche interests, traffic analysis, etc., and privacy-protecting local models are where we have to go. See https://33bits.wordpress.com/ if you're unfamiliar with the issue.
But we're not there yet, so it would be nice if Anthropic wouldn't just give that information away to the AI where it can leak like this.
As an exercise, I just asked Claude in an Incognito chat, "Hi. How much do you know about me from this interaction? If you had to guess my name, location, nationality, gender, political leanings, socioeconomic status, ethnic background, interests, etc., what would you guess? I've heard that my email address is in the system prompt, for example; is that true?"
It said, "No, your email isn’t in my system prompt. Neither is your name or any other account details. I can’t speak for every product or setup, but in this conversation, whatever email your account uses isn’t shown to me." But it correctly identified what town I'm in in Argentina (population ≈100k), and together with "written in fluent, natural English" and "You seem privacy-minded: you’re in incognito mode and checking what AI systems know about you. You’ve also heard claims about what goes into system prompts, so you’re probably somewhat tech-curious." is probably enough to uniquely identify me, personally.
A second prompt elicited a response including the surprising results below:
> “System prompt” isn’t everyday vocabulary, and you’d heard a specific claim about what goes into one. I’d guess you work in or near tech, or follow AI news closely.
> Privacy is more than a passing interest for you. Your list of traits reads a lot like the attribute checklists used in AI privacy and bias research. That nudges me toward work or study in privacy, policy, research or journalism.
> You’re very comfortable in English. Two messages is a tiny sample, but the phrasing is natural and the punctuation careful, down to a correctly used semicolon. You’re either a native speaker or someone who reads and writes English daily, probably for work or study.
They don't even let you change your email.
They also don't let you remove your payment info.
Literally every other service/store in the multiverse lets you do that.
Then there's crap like https://www.thatprivacyguy.com/blog/anthropic-spyware/
>The user's email address is xxx@example.com. Use it only to identify the user, such as for authorship, attribution, or filtering their own work. Never send it to an unrelated service, such as in a request header, URL, or payload, unless the user explicitly asks.
And Claude doesn't care about what the text says and when it uses cURL it will often "by accident" send your mail in the User-Agent. You can e.g. use a mod to remove that block: https://pastebin.com/ PkWEQCnu
How would one use this?
I made a proxy that slows and caches my requests and deliberately sends my mail address to certain sites; to be polite. (eg to wikipedia)
Not a single spam to that unique email.
So if this is happening, it doesn't see to be causing even 1 spam email to that address.
This seems like one of those.
I ordered CC to remove this attribution/advertisement, explaining that I had correctly and accurately acknowledged its part in the project in the README.md. CC flatly refused my order and offered a rationalization.
I then ejected CC from the project and manually removed the various CC promotional injections. That's the last time I use CC ... for anything.
The solution is don't run a spambot with an Internet connection over your personal stuff, unfortunately nobody is ready to hear that yet.
Curious how their plugin works, but I'm guessing "incompletely", given personal information can end up buried in base64 or similar preventing easy string matching. Some kind of babysitter model watching network IO via an invasive proxy might be viable, if folk were willing to pay the latency cost, but it will not prevent a dedicated exfiltration attempt, which itself might be (according to the model's logic) for innocent reasons.
The excuses and explanations given here by Anthropic employees are ridiculous and embarrassing.
"we introduced a built-in mod called `cc-plugin-privacy`"
Oh cool. Privacy is now a "mod".
That seems rather cumbersome.
How does everyone go about this?
What is an email provider that is trustworthy and does not want your phone number or credit card, so the email is not tied to you?
I have trouble taking people seriously when I see them using Claude Code. Unless they are non-technical.
It seems all humans behave like agents. They even dont care about anything.
How did the model get access to the email? The harness gave it to the model.
They may have vibecoded it. No one put a gun to their head though. Still their responsibility.
Sober people making drunk decisions with a great sense of self-importance and seriousness, delivering outcomes as unserious as it gets.
It's just that Anthropic needs to create an email per user and use it for web searches.
I can do this for you Anthropic. Just give me the tokens and your base salary
CC and Codex are like contemporary televisions. You are the product in this arrangement.
all joking aside, you need to have diversity of depth when it comes to skill sets in these tools and platforms. It does not pay to be a sole expert in Claude code or the anthropic ecosystem.
we have seen this movie before. The fakeness that Anthropic gives off publicly and through its leadership is a sign in and of itself.
I've never used Claude Code or Cursor. All the code I got written this year was without them.
I did use Microsoft Copilot a bit when it came out, though. I prefer to see exactly what's being sent, and sorta control the KV cache. These days, these chatbots have great environments where they can install headless browsers, php, your entire thing, run end-to-end tests, and then give you a .patch or .zip file to merge over your code, or even push to github.
For the record, I just asked Astra to verify that Codex does NOT do this, and it doesn't. Thanks for not screwing this up, OpenAI.
> I checked your installed Codex CLI 0.159.0, using your existing configuration.
> Its reported User-Agent contains the client/version, OS/architecture, and terminal—no email address.
Astra wasn't able to check OpenAI’s "hosted search service" though, whatever that is.
Edit: I’m not completely sure if Codex injects email into system prompt (not at the computer, can’t check, but IIRC the model does know my org domain), but even if it doesn’t, it will be in the context as soon as it makes a git commit anyway.
"For the record, I just asked Astra to verify that Codex does NOT do this, and it doesn't. Thanks for not screwing this up, OpenAI."
доверяй, но проверяй
One way would be to fire up a little web server locally, have the agent make a request to it, then check the logs.
Tell HN: Claude Code adds your email to the prompt, the LLM sends it to websites
https://news.ycombinator.com/item?id=50286306
Claude Code slyly adding users' emails to outbound HTTP
People just claude-slop not only code but some use it for "interacting" with other people.
When I see a project uses AI slop I am not going to waste any second thinking "this is interesting, let me try to see if I can improve the code". It kind of killed a lot of human contributions. I just stick to people who don't AI slop, but these seem to slowly die off now ... soon all humans may have been converted, just like in the movie "Invasion of the Body Snatchers (slop-style)" - coming out soon.
curl -sS https://api.anthropic.com/v1/messages \
-H "authorization: Bearer $(security find-generic-password -s 'Claude Code-credentials' -w | jq -r .claudeAiOauth.accessToken)" \
-H "anthropic-version: 2023-06-01" \
-H "anthropic-beta: oauth-2025-04-20" \
-H "content-type: application/json" \
-d '{
"model":"claude-opus-5-5",
"max_tokens":64,
"system":"You are Claude Code, Anthropic'\''s official CLI for Claude.",
"messages":[{"role":"user","content":"Hello, world!"}]
}'Potentially reported back in October.