Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...

ConsentFix and ClickFix attacks steal Microsoft 365 tokens in seconds using fake prompts and OAuth flows. Learn how these MFA ...

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

DirtyClone, tracked as CVE-2026-43503, is a Linux kernel vulnerability that allows any local user to gain root privileges.

A Connecticut man faces up to 10 years in prison for allegedly selling Windows 2000 and Windows NT source code stolen from a ...

Multiple weaponized proof-of-concept (PoC) exploits on GitHub delivered a Python-based remote access trojan (RAT) called ChocoPoC that can execute commands and steal sensitive data. However, ChocoPoC ...

A SimpleHelp authentication flaw is being exploited to deploy Djinn Stealer, a cross-platform malware targeting cloud, ...

GPT-5.6 was already running in Codex for some users before OpenAI’s government-approved preview opened to partners. A ...

The gold rush of desktop AI tools has made it incredibly easy to download rogue software or fall victim to supply chain ...

A set of 13 exploits were released by the Shadow Brokers hacker group, with Microsoft providing a rapid response, downplaying ...