Originally published on proxymint.

Claude Code's model put signed-in users' emails in User-Agent headers. What Anthropic confirmed, what is fixed, and how to check what your clients send.

TL;DR

  • If you're signed in, the model knows your email, and that's the root of it. Claude sometimes wrote that address into the User-Agent of its own curl call or script, for sites that ask for a contact. Anthropic staff confirmed this on 2026-11-06.
  • Update past the stable channel for now. Anthropic staff say to run 2.1.317 or later, which has the check. On 2026-11-07 npm's stable tag still pointed at 2.1.311.
  • The check is narrow, by its own README. It covers shell calls that name a User-Agent, and skips WebFetch, WebSearch, MCP tools and scripts. Staff say it "doesn't prevent all cases" and that the email leaves the model's context in the next release.
  • A proxy won't scrub this. Inside an HTTPS tunnel a normal proxy only forwards bytes, so what your client puts in its headers is what the site gets.

Key takeaways

  • Read your own headers before trusting any tool. A ten-second loopback listener shows exactly what curl, requests or your agent sends, and nothing leaves the machine.
  • Pin a plain User-Agent like mytool/1.0. No email and no project or client names, which one commenter found the model writing in too.
  • For contact details, HTTP already has From. RFC 9110 says a client shouldn't send it unless the user configured it, and the reporters say nobody asked them.
  • Grep ~/.claude/projects for your address. That's how commenters found past leaks in their own sessions.

Read the full guide on proxymint, with the commands, tables and sources.