On March 30, BeyondTrust proved that a crafted GitHub branch name could steal Codex’s OAuth token in cleartext. OpenAI classified it Critical P1. Two days later, Anthropic’s Claude Code source code ...
Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Three critical security vulnerabilities in Anthropic’s AI-powered coding tool, Claude Code, exposed developers to full machine takeover and credential theft simply by opening a project repository.
In the wake of Claude Code's source code leak, 5 actions enterprise security leaders should take now
Every enterprise running AI coding agents has just lost a layer of defense. On March 31, Anthropic accidentally shipped a 59.8 MB source map file inside version 2.1. ...
Results that may be inaccessible to you are currently showing.
Hide inaccessible results