Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle

Google Research · 1 week ago · 3

A workshop report from Google Contextual Agent Privacy and Security reviewed open and emergent privacy and security problems for autonomous, LLM-driven agents and proposed a contextual approach to evaluate actions. The report was developed for a late-2025 workshop held in New York City with more than 50 academic and industry leaders. It calls for multi-layer safeguards including sandboxing, context-aware policy engines, user controls, ecosystem governance, and new multi-agent benchmarks (“Agent Gym”) to measure risk over long-running interactions.