Path 1 of 6Foundation5 lessons · 46 minReviewed 2026-11-10
AI security fundamentals
How LLM applications and agents work as attack surface, the trust-boundary tests practitioners use, and the frameworks (OWASP, MITRE ATLAS, NIST) that give you shared vocabulary.
For: Security engineers, AppSec and SOC staff new to AI systems
- 01 How LLM applications and agents become attack surface
Map the parts of an LLM application, see where untrusted text enters, and explain why the trust boundary sits in your code rather than in the model.
9 min · 4 questions
- 02 The lethal trifecta and the Agents Rule of Two
Use two short design tests to decide whether an injected instruction can steal data or cause damage in a given agent, and which capability to remove or gate.
9 min · 4 questions
- 03 The OWASP LLM and Agentic Top 10 lists, in practice
Know what each entry of the two OWASP lists means for an engineer, how the lists relate, and how to use the ids in threat models, findings and detections without treating them as a checklist.
10 min · 4 questions
- 04 MITRE ATLAS: describing attacks on AI systems
Read ATLAS tactics, techniques, mitigations and case studies, and use ATLAS ids next to ATT&CK in detections, intelligence and red-team reports.
8 min · 4 questions
- 05 Threat-model an AI feature in an hour
Run a short, repeatable threat model for an LLM feature or agent: data flow, trust boundaries, the Rule of Two test, framework ids, controls, tests and logs.
10 min · 4 questions
Lessons cite primary sources and were last checked on the date shown in each lesson. Corrections are welcome by email (footer). Other paths: LLM applications · Agents & MCP · AI coding assistants · Red teaming · Detect & respond