How I stopped a massive WordPress spam attack with 4,700 lines of code in two days - thanks to Codex and Claude

Spam accounts overwhelmed my database. Claude found the weaknesses, Codex wrote the fixes, and I deployed a new defense.

New BioShocking attack manipulates AI browser into data theft

A new prompt injection attack dubbed "BioShocking" could trick AI-powered browsers into treating real-world risky actions as ...
SecurityWeek

Researchers Demo New Claude Code Attack Using Harmless-Looking Repositories to Hijack Developer Machines

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

‘DirtyClone’ Linux Kernel Vulnerability Leads to Root Access

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

SimpleHelp Flaw Exploited to Deploy Malware Targeting Windows, macOS, and Linux

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

AutoJack: How a single page can RCE the host running your AI agent

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 ...