AI agents now cross identity, tool, data, and infrastructure boundaries whenever they act on a user's behalf. AWS implementation guidance and attack activity observed by Wiz show why security controls must follow the complete path from user to model to tool.

As AI and third-party software operate on developer machines, workstations can hold direct paths to source code, credentials, and cloud environments. Wiz is framing the developer endpoint as a security perimeter that needs dedicated attention.

MCP creates a new connection surface between AI agents and internal tools. Cloudflare’s protocol-level detection signal suggests that effective governance starts with inventory, then moves to approved paths and enforcement.