Return to Threats

OpenAI’s Astra Crosses ‘Critical’ Cyber Threshold After Finding Zero-Days

securityweek.com 2026-09-02 malicious AI use Critical

Executive Summary

OpenAI's Astra crossed the 'Critical' cyber threshold, meaning it can independently find and exploit zero-days across many well-defended systems.

What Happened

The designation applies when a model can independently find and exploit zero-day vulnerabilities across many well-defended systems. The post OpenAI’s Astra Crosses ‘Critical’ Cyber Threshold After Finding Zero-Days appeared first on SecurityWeek .

Affected Products

  • OpenAI GPT-6 Astra

Vulnerability / Attack Technique

Autonomous vulnerability discovery and exploitation capability

Technical Mechanism

Capability evaluation.

AI Security Category

AI-assisted attack

Part of the AI-Assisted Attacks topic.

RealGround Analysis

Autonomous exploitation capability now exists at the frontier.

Recommended Controls

  • Shorten patch windows

Related RealGround Service

AI Red Teaming · or start with the free AI Agent Security Scanner.

Sources

securityweek.com: https://www.securityweek.com/openais-astra-becomes-first-model-to-cross-critical-cybersecurity-threshold/

Summary and analysis written by RealGround from the source above; last updated 2026-10-18.

Talk to AI CISO