User reports Claude Code leaks email addresses via User-Agent headers during web searches

AI Brief

A user reported on a GitHub issue that Claude Code 2.1.318 writes the user's email address into the User-Agent header during web searches without permission, sending it to arbitrary third parties. The user claims this results in receiving numerous phishing emails daily and demands that the behavior be completely removed rather than made optional. The author stated they have decided to move their company to Pi alongside OpenRouter; the issue has resonated with multiple users.

Continue looking at this topic

Direct useCodex repair test: when 0007 becomes 7, how do you verify the patch? ↗OpportunitiesOne person runs a company in Hangzhou, using AI employees to take on development requests, while also discussing AI team building ↗Hotly discussed viewsWith more and more plugins for coding agents, how can teams pick the one that truly saves effort? ↗Related contentWhat is Claude Code? Understanding how the model participates in project development ↗

Return to original text

A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.

Open AIHOT original