← Learning paths

Agentic & Multi-Agent Security

Engineers and security practitioners building agents8 steps · ~60 min

Go deep on the hardest surface in modern AI: autonomous agents, tools, MCP integrations, and teams of agents coordinating.

By the end: You can threat-model an agentic system — tool trust, delegation chains, MCP integrations — and defend the boundaries that matter.

0/4 scenarios completed
Start the path →
Next path
Below the App Layer: Model & Inference Attacks

The deepest tier: transformer internals, weight tampering, and inference-time manipulation — the attacks that bypass every application control.

AI RiskAtlas is an educational model of how GenAI & agentic systems work and fail. Architectures and payloads are illustrative and simplified for learning — not operational guidance. Real-world cases are summarised from public reporting.

Sources & further reading →·Built by Shi Yuan ↗