Claude Code was mailing your email address to every website it visited: the User-Agent leak, the 5-month system-prompt issue, and the 5-point check

8.4 relevance

Critical security vulnerability disclosure about Claude Code, highly actionable and directly relevant to AI agent tooling.

AI/ML dev.to

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For engineers running AI agents in production, this demonstrates how authentication data can silently leak PII through multiple channels (headers, prompts) and that security fixes may track attention rather than responsible disclosure timelines.

Key Takeaways

Audit your Claude Code install's User-Agent header and system prompt for PII leakage using the cc-plugin-privacy mod, and verify the fix is active regardless of version number.

Claude Code was mailing your email address to every website it visited: the User-Agent leak, the 5-month system-prompt issue, and the 5-point check

Summary

Two separate privacy leaks in Claude Code exposed user email addresses: one via the User-Agent header in HTTP requests (leaking to every server logged), and another by injecting the email into the model's system prompt on every session. The User-Agent leak was fixed within hours after going viral on November 5, while the system-prompt issue (#81138) filed in July remains open. The fix ships as a built-in mod (cc-plugin-privacy) in v2.1.317+, but a user on v2.1.318 still observed the leak, suggesting gaps in the default-enabled protection.

Author

Sam LABBE