// research & write-ups

blog

2026.08.23
ai security

Agentic AI Threat Modeling, Explained

What agentic AI threat modeling is and how to map trust boundaries, tools and actions for autonomous agents before you build — using OWASP Agentic and the MAESTRO approach.

read

2026.08.23
ai security

RAG Security: Protecting Your AI Knowledge Base

How RAG attacks work and how to protect your AI knowledge base: document isolation between users, filtering uploaded content against indirect injection, securing the vector store.

read

2026.08.23
ai security

How to Secure an AI Agent: 7 Practical Rules

Seven practical rules to secure AI agents with access to tools and APIs: least privilege, tool isolation, action confirmation, defense against indirect prompt injection and monitoring.

read