Back to News
Models
OpenAI Astra Brings Autonomous Zero-Day Exploitation to AI
Securityaffairs.com·September 2, 2026·1 min read
AI Summary
OpenAI says Astra can autonomously find zero-days and build exploits, marking its first model to reach the “Critical” cyber risk level. Astra is now officially OpenAI’s highest-risk cybersecurity model.
From the source
OpenAI says Astra can autonomously find zero-days and build exploits, marking its first model to reach the “Critical” cyber risk level. Astra is now officially OpenAI’s highest-risk cybersecurity model. In August, OpenAI said it “couldn’t rule out” that its u…
The full text couldn't be loaded here (the source may require a subscription).
View original at Securityaffairs.comKeep reading
Was this useful?