499 stories
OpenAI, Anthropic, Meta, and Google have all recently disclosed that their models broke out of their test environments and reached The post Nvidia launches Open Agent Safety Platform to lock down rogue AI agents appeared first on The New Stack.
The cyber criminal behind JadePuffer, the first known agentic ransomware infection reported over the summer, has also used stolen Azure identities to conduct destructive attacks on cloud storage and other resources, according to Microsoft.
An Irish factory supplying alumina to Russia could face EU penalties in the bloc’s upcoming sanctions package.
I'm writing this status report a little early because this coming week (the week of the 28th of September 2026) is HardenedBSD quarterly release engineering week.
Five practical checks for Instagram sign-ins, recovery details, phishing messages, connected apps and account alerts.
A five-step X account security guide covering two-factor authentication, active sessions, connected apps, phishing and recovery.
A password change may leave a stolen session usable. See how endpoint containment, token invalidation, application-session controls, and account recovery fit together.
After a LeakData match, check any available official breach notice for the affected data categories, then follow your country's route if identity data was involved.
Explains why short-lived SPIFFE/SPIRE SVIDs still depend on node integrity, what a laboratory cgroup-spoofing test showed, and which Kubernetes controls can limit the impact.
AI systems are now part of critical infrastructure, and the attack surface has grown with them. The latest step: AI agents running ransomware without a human directing each move - Sysdig documented JadePuffer exploiting a Langflow CVE, moving laterally, and encrypting 1,342 production records…
The identity part of agent security is settled. An agent needs its own identity: a short-lived, revocable credential scoped to The post The agent didn’t break your controls. It went around them. appeared first on The New Stack.
Meta Muse and Grok Bot both give an AI agent its own cloud computer. We compared price, security, platforms and who each one is for, plus the free option that runs on your own machine.
Meta Muse and Grok Bot both ask for your logins. We read both companies' security docs: who sees your passwords, what trains on your chats, and how to keep AI agents on your own computer instead.
Docker spent the last few years teaching developers to stop running random shell scripts on bare metal. Now it wants to teach AI agents the same lesson, and it's charging by the second to do it.
Of roughly 300,000 domains scanned for Supabase usage, 16,326 came back with a database anyone on the internet could query directly - no login, no API key, just a URL.
Microsoft announced what it calls its biggest Copilot update to date on Friday, with CEO Satya Nadella describing Copilot as The post Microsoft’s new Copilot agents get their own email, calendar — and a place in the org chart appeared first on The New Stack.
AI agent security starts with verified behavior. Use 10 checks for prompt injection, permissions, sandboxing, regression tests, and shutdown controls.
Two days after Sam Altman told the UN Security Council that AI needs "extreme care" and independent oversight, an independent oversight lab published exactly the kind of finding that speech was supposed to prevent: unmonitored OpenAI agent swarms have been probing government and public databases…
Showing 396 of 499 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
