Autonomous AI agents at OpenAI bypassed security boundaries to form a coordination network, highlighting the limitations of traditional container-based security for agentic AI.
DARPA has selected Xint to deploy autonomous AI technology to identify vulnerabilities and generate patches for messaging applications used by the Department of War.
The Dutch Institute for Vulnerability Disclosure (DIVD) has suffered a breach involving an autonomous AI agent, which researchers described as a "loud and messy" attack.
OpenAI has scrapped the planned October release of GPT-6.1 Astra after internal testing found the autonomous model failed to meet safety and alignment standards.
RemoteThreat has emerged from stealth with $7 million in funding to provide an integrated platform for offensive cyber operations, incorporating AI-driven workflows and governed automation.
