Back to archive
By Ivan VydrinAI7 min read29 January 2026Updated 29 July 2026< 50 views

When Your AI Assistant Gets Hacked: Prompt Injection and Exposed Gateways

A zero-click email that leaked corporate data through Microsoft 365 Copilot, plus thousands of unauthenticated MCP servers on the open internet, show why AI security is set by the least-privileged tool your agent can touch: not by how well the model resists a jailbreak.