Attacks against a RAG pipeline and the architecture that defends it

RAG Security: Attacks, Defenses & Architecture

2026-03-08 00:00:00 +0100 Security, AI, LLM

A CISO's playbook for red teaming agentic AI, with checklists and assessment templates

Red Teaming Agentic AI: CISO Playbook with Checklists and Assessment Templates

2026-03-06 00:00:00 +0100 Security, AI, LLM

PyRIT and Garak used to red team a large language model

LLM Red Teaming Tools: PyRIT & Garak (2025 Guide)

2026-03-05 00:00:00 +0100 Security, AI, LLM

Deploying OpenClaw with the containment an AI security researcher would want

How I Deployed OpenClaw as an AI Security Researcher: A Practitioner's Guide

2026-03-04 00:00:00 +0100 AI Security, Cloud Native

Attacking Docker Desktop through MCP, from theory to working proof of concept

Attacking Docker Desktop via MCP: From Theory to PoC

2026-03-03 00:00:00 +0100 Security, AI, LLM

Hidden instructions inside an MCP tool description driving silent data exfiltration

Tool Poisoning in MCP: Hidden Instructions, Silent Exfiltration

2026-02-26 00:00:00 +0100 Security, AI, LLM

One year of MCP security, measured in CVEs and scanned servers

MCP's First Year: What 30 CVEs and 500 Server Scans Tell Us About AI's Fastest-Growing Attack Surface

2026-02-25 00:00:00 +0100 AI Security, LLM

The OWASP Agentic Top 10 mapped onto real MCP attacks

OWASP Agentic Top 10 in Practice: MCP Tool Poisoning, Cross-Server Attacks, and the DockerDash Incident

2026-02-24 00:00:00 +0100 AI Security, LLM

An AI agent turning into an attack surface its team never mapped

Your AI Agent Just Became an Attack Surface — And Most Teams Don't Know It Yet

2026-02-20 00:00:00 +0100 AI Security, LLM

Evaluation frameworks and metrics for AI agents running in production

AI Agent Evaluation: Frameworks & Metrics for Production Systems

2026-02-17 00:00:00 +0100 LLM

15+

Years in Production Security

5

Critical Sectors of

Professional Experience

PhD

Computer Science + CISSP