SecurityDark Readingabout 2 hours ago
Anthropic patches zero-click AI flaw
3 min read
Anthropic fixed a zero-click bug in Claude Code Desktop on Aug. 17 after Noma researchers bypassed an initial July 9 patch. The flaw allowed attackers to steal AWS credentials, SSH keys, and OAuth tokens via a malicious HTML file in the preview pane, exposing developer machines to silent credential theft without user interaction.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
