OWASP GenAI LLM Top 10 2026: What the New Rankings Mean for Security Teams

The OWASP GenAI LLM Top 10 2026 was published on August 3, 2026. I am still learning my way around AI security, and I read OWASP Top 10 lists because they are the closest thing the industry has to a consensus map. They are not academic papers. They become the basis for threat models, security review checklists, and procurement questions. The GenAI edition specifically maps the risks that matter when you build applications around large language models. ...

August 5, 2026 · 6 min · 1111 words · Matteo Bisi

Securely Working with Third-Party MCP Servers

In the rapidly evolving landscape of AI and large language models (LLMs), the ability to connect these models to external tools and data sources is crucial for building powerful, automated applications. The Model Context Protocol (MCP) has emerged as a standard for this purpose, but its use also introduces new security challenges. This article explores how to work securely with third-party MCP servers, drawing insights from the recently released OWASP GenAI security cheatsheet. ...

November 17, 2025 · 4 min · 668 words · Matteo Bisi