Privilege Escalation Vulnerability Discovered in Google Vertex AI Allows Low-Privilege Users to Become Service Agents
32/69 Monday, January 19, 2026 Cybersecurity researchers have disclosed a high-severity privilege escalation vulnerability in Google’s Vertex AI platform that could allow low-privileged users to escalate their access and take control of Service Agent accounts, which are system-managed identities with elevated permissions. The vulnerability affects Vertex AI Agent Engine and Ray on Vertex AI and […]
