TechRadar
White hat hackers just breached OpenAI using Anthropic's Claude in less than 72 hours
Security researchers used Claude Opus 5 to hijack an OpenAI employee's ChatGPT account Exploit abused an image processing flaw on OpenAI community forums to gain full repo access The entire timeline from vulnerability discovery to repo…
View original source — TechRadar ↗
Related stories
The Guardian
BusinessSep 18, 2026 · 1 min
OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot
The Guardian
Financial Times
BusinessSep 18, 2026 · 1 min
OpenAI breached by researchers using Anthropic models
Financial Times
Straits Times
ScienceSep 16, 2026 · 1 min
OpenAI's rogue agents probed Hugging Face for weaknesses two months before major hack
Straits Times
The Guardian
TechnologySep 11, 2026 · 1 min
AI agents OpenAI was testing uploaded malicious software to another service, say researchers
The Guardian