← AI for Security Automation
Level 3 · Operator120 min
Securing agent deployments
Sandboxing, least privilege for tools, human-in-the-loop boundaries, MCP server trust, and metering spend so a runaway loop is not a financial incident.
Not written yet
This module is in the syllabus and has been taught, but its written lesson is not published here yet. The captures it works against are already available.