Prompt Injection Security

The chapters in this module, in reading order.

#	Chapter
00	AI Security and Red-Teaming — First-Principles Overview
01	Threat-model an AI system — map reachable harm before arguing about prompts
02	Direct prompt injection — the user tries to become the system
03	Indirect prompt injection — hostile instructions hidden in trusted-looking content
04	Jailbreaks and policy pressure — attacks against refusal behavior
05	Data exfiltration and secrets — the model must not become a leak path
06	Tool abuse and action boundaries — text becomes impact
07	Memory and cross-tenant risk — yesterday's text can attack tomorrow
08	Red-team evals and scoring — adversarial tests that change releases
09	Security controls and isolation — hard boundaries around a persuasive model
10	Security monitoring and response — from suspicious trace to incident
11	Honest admission — what AI security still cannot guarantee