Anthropic's Opus 4.6 system card breaks out prompt injection attack success rates by surface, attempt count, and safeguard ...

AI assistants apparently can't distinguish between instructions and data, and that is at the center of many zero-click prompt ...

Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in which private-sector firms and researchers use legitimate API access to ...

Docker patched a critical Ask Gordon AI flaw enabling code execution and data theft via malicious image metadata in version 4 ...

The company, which got its start making powerful command line terminal software, has expanded to a platform for controlling ...

A report by GreyNoise warns the IP address is operating behind bulletproof hosting infrastructure and might not show up in ...

Ivanti has disclosed two critical vulnerabilities in Ivanti Endpoint Manager Mobile (EPMM), tracked as CVE-2026-1281 and CVE-2026-1340, that were exploited in zero-day attacks.

AI agents are a risky business. Even when stuck inside the chatbox window, LLMs will make mistakes and behave badly. Once they have tools that they can use to interact with the ou ...

Deno Sandbox works in tandem with Deno Deploy—now in GA—to secure workloads where code must be generated, evaluated, or ...

Meanwhile, IP-stealing 'distillation attacks' on the rise A Chinese government hacking group that has been sanctioned for targeting America's critical infrastructure used Google's AI chatbot, Gemini, ...

Anthropic has launched Claude Cowork for Windows, bringing its AI agent’s file access and task automation to most desktop users as Microsoft deepens its partnership with Anthropic while reassessing ...