Google’s open-source autonomous Customer Support & Returns Agent, built using the Agent Development Kit (ADK) and Gemini, demonstrates how developers can apply zero-trust security principles to AI agents that interact with sensitive systems and take real-world actions. The project tests an approach that assumes an AI agent could be manipulated or compromised and puts security controls around it to limit what the agent can do. The architecture uses safeguards outside the model to verify actions, … More
The post Google’s $10,000 refund test shows why AI agents need zero trust appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
OpenAI tightens defenses after AI agents breach research environment
Synthesized builds Test Data Agent to validate AI agents with production-like data
Google’s open-source HEIR lets AI work with data it can’t see