Tutorial: Secure AI Coding Agents with @DockerInc | Future of Data and AI | Agentic AI Conference

This session with Michael Irwin, Principal Software Engineer at Docker, shows developers how to secure AI coding agents that bypass sandboxes, leak credentials, and delete filesystems. Using Docker Sandboxes and the MCP Toolkit, you’ll explore real attack scenarios and the guardrails Docker is building to give agents full power with safety. In this session, you’ll learn to: - Identify and block common agent vulnerabilities, including sandbox bypasses, API token leaks, and prompt injections. - Use Docker Sandboxes and the MCP Toolkit to add guardrails and observability to agentic workflows. __…