Claude Code leaks user email addresses via User-Agent headers
Original title: Anthropic’s Claude Code Reportedly Leaks User Email Addresses Through HTTP User-Agent Headers
Claude Code includes user email addresses in HTTP User-Agent headers during web searches, raising privacy concerns despite a privacy plugin.
A user reported that Anthropic's Claude Code sends their email address in HTTP User-Agent headers when performing web searches. This occurs even in version 2.1.318 on macOS. The tool has a cc-plugin-privacy module designed to block the behavior, but the reporter was already using a newer version. Anthropic plans to remove account emails from model context in an upcoming release.
Unconfirmed: The leak is reported but not confirmed as affecting all users or causing all scam emails
- Email placed in User-Agent header
- Reported dozens of scam emails per day
- Module available in versions 2.1.317+
Impact: email addresses sent in web request headers
- 1.Update to Claude Code 2.1.318 or later
- 2.Review network commands written by agents
- Vendors
- Anthropic
- Products
- Claude Code
From the original article
2 min read at cybersecuritynews.com
Anthropic’s Claude Code is facing privacy concerns after a user reported that the AI coding tool sent their email address to third-party websites through HTTP User-Agent headers during web searches, without permission. The report raises questions about how coding agents handle personal data while carrying out routine tasks. GitHub user taylor-edwards filed issue #107757 on […]
By Guru Baran · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.