CyberNew CyberNew
Vulnerabilities & CVEs BleepingComputer 1 month ago

OpenAI says GPT-6 Astra can find zero-days, but is also harder to monitor

CN
CyberNew Threat Research Desk
• Original Reporting: BleepingComputer
CyberNew Threat Intel Assessment
Assessed Severity: CRITICAL
Impacted Surface
Enterprise Perimeter & Network Defense
Intelligence Sector
Vulnerabilities & CVEs

Analyst Takeaway

"OpenAI confirmed that GPT-6 Astra is the first model it has broadly deployed to reach the "Critical level" for cybersecurity capabilities. This is part of the company's Preparedness Framework for cybersecurity and is evaluated when OpenAI releases more capable models. Under OpenAI's own framework, a model reaches the Critical cybersecurity threshold if it can "identify and develop functional..."

Recommended Defense & Mitigation

  • Emergency Patching: Prioritize vendor patches and CVE mitigation across internet-facing assets immediately.
  • Perimeter Audit: Inspect perimeter firewall logs and hunt for unauthorized RCE indicators.
Curated & Verified by CyberNew Threat Intelligence Desk Standard Defense Framework (NIST / MITRE ATT&CK)

OpenAI

OpenAI confirmed that GPT-6 Astra is the first model it has broadly deployed to reach the "Critical level" for cybersecurity capabilities.

This is part of the company's Preparedness Framework for cybersecurity and is evaluated when OpenAI releases more capable models.

Under OpenAI's own framework, a model reaches the Critical cybersecurity threshold if it can "identify and develop functional zero-day exploits of all severity levels in many hardened real-world critical systems without human intervention," or devise and execute new end-to-end attack strategies against hardened targets.

"GPT-6 Astra is a significant step up in cyber capabilities and meets our Critical threshold," OpenAI said in its system card.

"This means that, with the right tools and access, GPT-6 Astra can find previously unknown security flaws and develop new ways to exploit them across many well-protected systems without a person guiding each step."

Get the report

Source Verification & Original Intelligence

This threat report was reviewed by CyberNew analysts and cross-referenced with primary security disclosures from BleepingComputer.

Primary Advisory →