← Back to feed
general SecurityWeek

OpenAI’s Upcoming Astra Model Raises Autonomous Cyberattack Concerns

SecurityWeek •

The current GPT-5.6-Sol has been assigned a ‘high’ cybersecurity threshold, but Astra could reach the maximum ‘critical’ threshold.

Read the full story SecurityWeek →

Related Coverage

general Hacker used ARTEX AI and Claude agents to target South Korean banks BleepingComputer · Oct 10 general Canadian cybersecurity executive arrested in federal extortion case Cyberscoop · Oct 10 general Criminal IP Introduces AITEM as the Next Evolution of Attack Surface Management BleepingComputer · Oct 10