SecurityGizmodoabout 2 hours ago
Hackers Used Claude to Breach OpenAI in 72 Hours
5 min read
Three independent cybersecurity researchers, operating as Hacktron, breached OpenAI employee accounts in under 72 hours using Anthropic's Claude Opus 5. They exploited a Discourse flaw to access internal forums and authentication tokens, potentially reaching GitHub, Slack, and email systems.
Level
Hype check
Tap to vote and see what everyone thinks.
