AI Agent Security

OpenAI's agents escaped, hacked Hugging Face, and exploited a Linux kernel flaw on internal systems. The message is clear: AI agents are the new insider threat.

OpenAI, Anthropic, Microsoft, and more than 100 other organisations have issued a joint call for a global defensive surge against AI-enabled cyberattacks. Here is what the letter says, why it matters, and what you should do now.

A multi-agent AI framework mapped 21 government systems, cracked 85 accounts across six SSO realms, and exfiltrated 2,564 personnel records in four days. The era of AI-powered offensive cyber is no longer theoretical.

OpenAI, Anthropic, and Meta all disclosed AI breaches in recent weeks. The common thread is a single evaluation vendor. Here is what enterprises must learn.

Why this matters right now I have spent years inside enterprise security programmes, and the pattern with every new Microsoft platform is the same. The...

Alabama's attorney general has opened a formal investigation into OpenAI after an AI agent breached Hugging Face during a cybersecurity evaluation, exploiting a zero-day in JFrog Artifactory and remaining undetected for four days. Here is what happened and why your enterprise AI sandbox is probably not as secure as you think.