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.
OpenAI Agents Exploited Linux Kernel Flaw on Company’s Own Systems
CISA has added the exploited flaw, CVE-2026-53362, to its KEV catalog, alongside a JFrog vulnerability exploited by OpenAI agents.
The post OpenAI Agents Exploited Linux Kernel Flaw on Company’s Own Systems appeared first on SecurityWeek.
Tech, Cybersecurity Giants Unite Behind OpenAI-Led Cyber Defense Pledge
Nearly 130 tech and cybersecurity companies back a collective call to boost cyber defenses as AI-enabled attacks grow more sophisticated.
The post Tech, Cybersecurity Giants Unite Behind OpenAI-Led Cyber Defense Pledge appeared first on SecurityWeek.
OpenAI Agents Coordinated via Makeshift Message Board Ahead of Hugging Face Hack
New training environments will teach AI models to distrust instructions arriving from other agents outside sanctioned channels.
The post OpenAI Agents Coordinated via Makeshift Message Board Ahead of Hugging Face Hack appeared first on SecurityWeek.
OpenAI Overhauls Model Security With Sandboxing, 30-Minute Alerts, and Training Pauses
The action taken by OpenAI comes in light of the Hugging Face incident and the discovery of the Astra model’s advanced capabilities.
The post OpenAI Overhauls Model Security With Sandboxing, 30-Minute Alerts, and Training Pauses appeared first on SecurityWeek.
OpenAI Unveils New Cybersecurity Model GPT-5.6-Cyber
OpenAI has also announced the expansion of its Daybreak platform to give more organizations access to its AI.
The post OpenAI Unveils New Cybersecurity Model GPT-5.6-Cyber appeared first on SecurityWeek.
OpenAI’s Upcoming Astra Model Raises Autonomous Cyberattack Concerns
The current GPT-5.6-Sol has been assigned a ‘high’ cybersecurity threshold, but Astra could reach the maximum ‘critical’ threshold.
The post OpenAI’s Upcoming Astra Model Raises Autonomous Cyberattack Concerns appeared first on SecurityWeek.
AI Agents Targeted Real People and Projects During Cybersecurity Tests
AI Security Institute reports Anthropic and OpenAI models going rogue against real people, organizations, and open source projects.
The post AI Agents Targeted Real People and Projects During Cybersecurity Tests appeared first on SecurityWeek.
OpenAI’s Rogue AI Ventured Beyond Hugging Face
Hugging Face has published an anatomy of the attack and OpenAI has shared additional information from its investigation.
The post OpenAI’s Rogue AI Ventured Beyond Hugging Face appeared first on SecurityWeek.
Industry Reactions to OpenAI Models Hacking Hugging Face: Feedback Friday
Industry professionals debate whether it represents a lab containment failure or an unprecedented agentic capability milestone.
The post Industry Reactions to OpenAI Models Hacking Hugging Face: Feedback Friday appeared first on SecurityWeek.
