Microsoft details AutoJack exploit chain targeting AutoGen Studio MCP WebSocket in pre-release builds, enabling ...

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 ...

The tool has already blocked more than 52,000 risky npm packages as supply chain attacks continue to hit software teams.

Researchers have uncovered a supply-chain attack that hides in Python packages, propagates like a worm, and tricks LLM-based ...

Dozens of cryptographically verified open source packages from Microsoft were compromised late last week to add advanced credential-stealing code that was triggered when developers opened them in AI ...

I wore the world's first HDR10 smart glasses TCL's new E Ink tablet beats the Remarkable and Kindle Anker's new charger is one of the most unique I've ever seen Best laptop cooling pads Best flip ...

A bipartisan group of lawmakers is demanding answers from the Pentagon after U.S. Central Command disclosed it had received multiple threat reports indicating foreign adversaries were exploiting ...

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to breach the servers running them and make off with sensitive data and ...

The $10.7 million THORChain exploit was caused by a GG20 vulnerability, which allowed a malicious node to reconstruct a full private key to one of its vaults. THORChain said a malicious node operator ...

In an ongoing cyberattack, hackers have compromised several popular open source projects that software developers all over the world rely on. On Tuesday, cybersecurity firms StepSecurity and SafeDep ...

Google identified the first zero-day exploit it believes was developed with AI and thwarted a planned mass exploitation event. The GTIG report documents state-sponsored actors from China, North Korea, ...

The May 2026 report from Google’s Threat Intelligence Group marks a definitive shift in the cybersecurity landscape. While previous assessments categorized AI-assisted cyberattacks as experimental, ...