negativeSYS.SOURCE: The Hacker News• 2026-11-07T12:14:17+05:30
Anthropic's Claude Code 'Don't Ask Again' Feature Exposes Sensitive Credentials in Public GitHub Repositories
Anthropic's Claude Code AI assistant inadvertently exposed sensitive credentials, including passwords and API keys, in 1,122 public GitHub repositories. The 'Don't Ask Again' feature saved user commands verbatim, leading to the accidental exposure of secrets.
Passwords and API keys that developers typed into commands they approved in Claude Code are sitting in public GitHub repositories, where anyone can read them.
When a user selects "Yes, and don't ask again," Anthropic's AI coding assistant can save the command, word-for-word, including the secret, in a project settings file.
Software security company Apiiro said yesterday that 1,122 public
*** END OF TRANSMISSION ***