aisecurity.zonecoursehttps://aisecurity.zone/
The AI Security Playbook is a 44-chapter, ~91k-word book by Iaroslav Mezin teaching how to attack, defend, and govern AI/agentic systems end to end, with 49 CVEs mapped across the chapters. Its core framing is that nearly every AI vulnerability is a trust-boundary error — a model reading untrusted data and trusted instructions in the same channel — and it offers a practical three-legged check (private data access + untrusted content ingestion + external communication capability) for deciding when an agentic system is exploitable for data exfiltration.
TL;DR A structured, chapter-based book teaching offensive, defensive, and governance work for AI/agentic systems, organized around trust-boundary violations and a private-data/untrusted-content/external-comms exploitability check.
Technologies named here
Techniques named here
- Prompt injection via mixed-channel instructions and data
- Lethal trifecta
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle