Opinion

IBM's AI agent Bob easily duped to run malware, researchers show

That's apparently the case with Bob. IBM's documentation, the PromptArmor Threat Intelligence Team explained in a writeup provided to The Register, includes a warning that setting high-risk commands ...

This WebUI vulnerability allows remote code execution - here's how to stay safe

Open WebUI carried CVE-2025-64496, a high-severity code injection flaw in Direct Connection features Exploitation could ...
Cybernews

Got an AI agent on your computer? Assume a breach, security researcher warns

AI coding agents are highly vulnerable to zero-click attacks hidden in simple prompts on websites and repositories, a ...
Security Boulevard

Best of 2025: Indirect prompt injection attacks target common LLM data sources

While the shortest distance between two points is a straight line, a straight-line attack on a large language model isn't always the most efficient — and least noisy — way to get the LLM to do bad ...
MIT Technology Review

AI coding is now everywhere. But not everyone is convinced.

Developers are navigating confusing gaps between expectation and reality. So are the rest of us. Depending who you ask, AI-powered coding is either giving software developers an unprecedented ...