Cybersecurity researchers at Mindguard have disclosed a prompt injection vulnerability in Amazon Kiro, an AI-powered agentic integrated development environment (IDE), that could…
A solo Russian-speaking threat actor known as "bandcampro" has been observed using Google's open-source Gemini CLI AI to control a botnet of…
Researchers from Tel Aviv University, Technion, and Intuit have identified a novel attack vector called HalluSquatting that exploits AI coding assistants' tendency…
Vulnerabilities in Google Gemini CLI allow a sandboxed attacker to escape the container boundary and run arbitrary code on the host, as…