Claude Code Command Leaks Credentials to Public GitHub Repos

A command in Anthropic's Claude Code can inadvertently commit files containing credentials and other sensitive data to public GitHub repositories, exposing organizational secrets. The vulnerability stems from default behavior that saves files without proper redaction, and the full scope of affected organizations remains unclear. This highlights a growing security risk as AI coding tools become more integrated into development workflows.

AI disclosure: Model-written summary of the source, not a verified fact. Check the sources. How Mosaic works