…In this system, we take open source applications where vulnerabilities were previously discovered, freeze them at the vulnerable version, and run our agents against them. But this time, we expanded our testing…
…Models are pre-trained AI systems hosted on the platform comprising weight files, configuration, and code. Researchers at HiddenLayer, a company focused on safeguarding AI and ML models against attacks, discovered the…
…CISA orders feds to patch Gogs RCE flaw exploited in zero-day attacks Max-severity flaw in ChromaDB for AI apps allows server hijacking KnowledgeDeliver flaw exploited as a zero-day to…
Why AI-driven threats are exposing the limits of MSP security stacks Sponsored by Kaseya June 11, 2026 10:00 AM AI is transforming the speed and scale of cybercrime in ways…
…13-year-old bug in ActiveMQ lets hackers remotely execute commands Max severity Flowise RCE vulnerability now exploited in attacks CISA: New Langflow flaw actively exploited to hijack AI workflows Fortinet warns…
…What the Tutorial Shows "Hercules" explains how to monetize a vulnerability discovery in the wild. He begins with advice on how to search for newly disclosed vulnerabilities, especially high-impact classes such…
…Between July 21 and August 6, OpenAI , Anthropic , Meta , Moonshot AI , and the UK AI Security Institute disclosed incidents in which AI agents acted outside their intended scope. Agents escaped evaluation environments…
…The rise of non-human identities — AI agents, service principals, automated workflows — has changed what a compromise in Entra ID can look like. "In today's AI era, a lot of identities…
…Hackers target US firms in FastJson RCE zero-day attacks CISA orders urgent action on actively exploited Langflow RCE flaw Critical Langflow RCE flaw exploited to hack AI app servers Arbitrary File…
Chinese hackers target telcos with new Linux, Windows malware By Bill Toulas May 21, 2026 10:00 AM A Chinese cyber-espionage campaign has been targeting telecommunications providers with newly discovered Linux…