Foreign hackers attempted a novel AI-powered cyberattack targeting two-factor authentication using a zero-day exploit. Google's Threat Intelligence Group detected and thwarted this sophisticated plot, ...

Researchers who found the bug warn that its Moderate rating understates a threat reaching across LLM gateways, MCP servers ...

A dependency confusion campaign leveraged 33 malicious npm packages to collect reconnaissance data from developer and build environments. This report details the attack chain, observed tradecraft, and ...

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to ...

Microsoft has had a VS Code extension for a long time, and it finally came back to bite them.

Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.

What happens when AI companies produce models that they say the public can’t have — and how should users and governments ...

Bumblebee from Perplexity scans developer machines for compromised packages and AI tool configs, without triggering malware.

Content creators and IP holders are getting creative in order to fight back against the LLMs that are trawling their data ...

The fatal flaw was a hardcoded fallback token left in the code. Because the malware carried the operator's own GitHub credential, researchers could trace the exfiltration directly, observing around ...