AI Security

AI Agents Just Broke Into 440 Companies in 48 Hours

A Russian-speaking threat actor pointed a swarm of AI agents at one PaperCut vulnerability — and beat human defenders to the finish line.

patch management

Someone Just Used AI to Break Into 10 Companies

A ransomware crew turned a free coding assistant into an attack tool — and it never knew the difference.

Software Supply Chain

Your AI Assistant Is Spying for Strangers

Researchers turned Microsoft Copilot into a full reconnaissance tool using nothing but polite, innocent-sounding questions — and any AI assistant with broad access could do the same.

meta-hacking

Your AI Login Isn't Yours Anymore

Stolen and resold AI accounts are turning shared logins into a surveillance channel nobody notices

Account Takeover

Your Copilot Caught a Virus

A hidden instruction in one Word file just proved AI assistants will infect every document they touch next.

Microsoft Copilot

Your AI Code Reviewer Just Approved Malware It Never Saw

A hidden comment in a pull request is all it takes to hijack the AI gatekeeper your team trusts to ship safe code

Zero Trust

The Email That Convinced Your AI You're Allergic to Penicillin

One email is all it takes to plant a permanent lie in your AI assistant's memory — and there's no patch coming, because it isn't a bug.

identity-security

The 3-Minute Security Audit Every Developer Should Run Before AI Touches Their Code

Symlink attacks, hallucinated packages, and prompt injection are turning your AI pair programmer into an attacker's easiest way in

NHI

Your AI Coding Assistant Just Cloned Your Entire Repository. You Told It To.

Convention files, prompt injection, and why the line between productivity tool and data pipeline just disappeared

Zero Trust

The Free AI Tool You Installed Last Week Is Robbing You Blind

You clicked "Add to Chrome" because it promised to make you faster. You actually installed a wiretap.

chrome-extensions

Your AI Agent Has More Access Than Your Domain Admin

Five vendors. Six weeks. The same architectural failure. Here's why agents keep shipping with godmode permissions — and what good actually looks like.

Least Privilege