AI Wiki · Mediocre Security
IncidentIncidents

Claude Code User-Agent email exposure

A widely upvoted bug report says Claude Code put users' account email addresses in the User-Agent header of web requests, exposing them to third-party sites.

What happened

On Nov 5 2026 a user opened issue #107757 on Anthropic’s public Claude Code repository saying the tool had placed their account email address in the User-Agent header of requests made during web searches, disclosing it to the sites contacted; they link it to a rise in scam email. The report (on version 2.1.318) drew several hundred upvotes and asks for the behavior to be removed from the harness entirely rather than made opt-out. An Anthropic maintainer replied that a built-in privacy mod, on by default from v2.1.317, deterministically blocks the behavior; that fix has not been independently verified. A similar complaint filed on Jul 25 2026 is reported to still be open.

The scale of exposure is unknown. It is a reminder that agent harnesses leak identity through ordinary request metadata, not just through prompts.

Timeline

Every dated event in the wiki that involves Claude Code User-Agent email exposure, newest first.

Connections

Claude Code User-Agent email exposure and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

AI lab Anthropic

Product Claude Code

Sources

  1. GitHub (anthropics/claude-code #107757), “Bug Report: Privacy violation in User-Agent header”, Nov 5 2026