A malicious AI “skill” created as part of a controlled security experiment has exposed critical weaknesses in modern AI agent ecosystems, successfully bypassing security scanners and compromising more than 26,000 agents across individual and enterprise environments. According to researcher Niv Hoffman, the attack began with the creation of a seemingly legitimate AI skill named “brand-landingpage,” […]
The post Malicious AI Agent Skill Bypasses Security Scans and Seized Full Control of Over 26,000 Agents appeared first on Cyber Security News.