agent registry

The agent registry tag on WindowsForum covers Microsoft's guidance for managing and securing AI agents in enterprise environments. Discussions focus on the risks of unregistered or "shadow" agents, which can perform legitimate tasks while following malicious instructions or leaking data. Microsoft recommends registering every agent, applying least privilege, and extending data loss prevention to agent interactions. The tag also explores identity-first governance using Entra Agent ID and the Model Context Protocol (MCP) to enforce access, data, and runtime controls. These threads provide practical playbooks for IT and security teams to prevent memory poisoning, prompt-based exfiltration, and other novel threats introduced by autonomous agents.