GPT-6 Astra Is the First Model OpenAI Classifies as Critical for Cybersecurity
September 17, 2026
1 min read
3 views
cybersecurity
news
newsapi
OpenAI has classified GPT-6 Astra at the Critical cybersecurity threshold under its Preparedness Framework, a first. In expert-led testing the model found previously unknown vulnerabilities in a browser and an OS kernel and built working exploits. The same sy
Was this article helpful?
0 found this helpful