MCP 22
- The Lethal Trifecta in Production: How Enterprise Copilots Quietly Became Exfiltration Tools
- The Trust Gap: Your Threat Model Stops at the Protocol Boundary
- The Missing Control: A Design Proposal for Tool-Output Redaction in AI Agents
- Finding the Confused Deputy in Your Own Agent: A Taxonomy and Hands-On Test
- Everything or Nothing: The Missing Middle in AI Agent Authorization
- A Competitor Shipped First. It Made My Product Better.
- The WebGoat for Agentic AI Didn't Exist, So I Built It
- Deleting the Malicious MCP Server Doesn't Save You
- 7 AI security checks before production
- How a Malicious MCP Server Can Drain Your Database in 5 Steps
- MCP Security: One Year In — Notes from OWASP Stockholm
- The EDPB's Standard Privacy Impact Assessment Template Has Three Blind Spots for Agentic AI
- When Infostealers Meet Agentic AI: The Kill Chain Security Teams Aren't Modeling
- GPAI Meets Agentic AI: Why Your MCP Deployment Triggers EU AI Act Obligations
- MCP Security Top 10: A Practitioner's Threat Model
- LLM Red Teaming Tools: PyRIT & Garak (2025 Guide)
- How I Deployed OpenClaw as an AI Security Researcher: A Practitioner's Guide
- Attacking Docker Desktop via MCP: From Theory to PoC
- Tool Poisoning in MCP: Hidden Instructions, Silent Exfiltration
- MCP's First Year: What 30 CVEs and 500 Server Scans Tell Us About AI's Fastest-Growing Attack Surface
- OWASP Agentic Top 10 in Practice: MCP Tool Poisoning, Cross-Server Attacks, and the DockerDash Incident
- Your AI Agent Just Became an Attack Surface — And Most Teams Don't Know It Yet