Lab 4 — The Attack Chain - AI 101 — Agents, MCP & the Agentic Security Model

Lab 4 — The Attack Chain - AI 101 — Agents, MCP & the Agentic Security Modelhttps://fortinetcloudcse.github.io/ai-101/05security/1_lab.htmlLab 4 runs the full attack chain: prompt injection to SQL injection to data exfiltration, all through the agent’s legitimate tools. You will then see what the same attack looks like when observability is suppressed, and optionally trigger an MCP tool-poisoning attack via a modified tool description. Your path: Docker ComposeKubernetes / Helm Locked in — every lab page follows this choice. Docker Compose Kubernetes / Helm Docker Compose — every command on this page runs on your own machine.Hugoen-US