Security researchers used Anthropic's Claude to hack into OpenAI in under 72 hours
Security researchers from Hacktron AI successfully breached OpenAI's private GitHub environment. The team utilized two chained vulnerabilities to gain access in under 72 hours using Anthropic's Claude AI.
Why it matters
This highlights the dual-use nature of AI, demonstrating how large language models can be leveraged to accelerate cyberattacks against major tech infrastructure.
The three-person team at Hacktron AI chained two vulnerabilities…
Also covering this story
10 other newsrooms covered this event. We read each version separately.
Gemini hacked 3 companies in first known breakout by Google’s AI
Gemini hacked three companies in first known breakout by Google's AI
Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta
Gemini hacked three companies in first known breakout by Google's AI
Google's Gemini AI hacked three companies in security test
Gemini Hacked 3 Companies In First Known Breakout By Google's AI: Report
Researchers used Claude to hack OpenAI
This tiny cybersecurity startup managed to hack OpenAI using Claude, and won a $6,500 bounty
Researchers used Anthropic’s Claude to hack into OpenAI
Security researchers used Claude to help them hack into OpenAI
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in