Google Shares Safety Guardrails for Chrome Browser’s Agentic Capabilities

Google has detailed the security architecture behind Chrome’s new agentic features, aiming to protect users from risks such as prompt injection and malicious website behaviour. The system includes a separate “user alignment critic” to verify agent actions, stricter origin isolation, mandatory user confirmations for sensitive tasks and real-time threat detection. Google says these layers prepare Chrome for an “agentic web” where AI agents take a more active role in browsing.