Vincenzo Ciancaglini
5 articles
-
AI and Emerging TechnologiesStars Don’t Save You: Popularity Is Not Security in the MCP Ecosystem
Building on our previous research, we correlated the security issues identified in public MCP servers with metadata crawled from popular directories. We then analyzed whether indicators such as popularity, activity, and vetting serve as reliable metrics to infer the risk of adopting an MCP server.
June 24th, 2026Vincenzo Ciancaglini, Marco Balduzzi, Alfredo Oliveira, David Fiser
Read article -
AI and Emerging TechnologiesThe Devil Reviews Xanthorox: A Criminal-Focused Analysis of the Latest Malicious LLM Offering
Xanthorox AI: flirty, menacing, and potentially devastating? We explored the inner workings of this LLM to unveil its devious capabilities for generating malicious code, obtaining private information, and roleplaying.
November 11th, 2025 15 minDavid Sancho, Vincenzo Ciancaglini, Salvatore Gariuolo
Read article -
AI and Emerging TechnologiesThe Road to Agentic AI: Navigating Architecture, Threats, and Solutions
As agentic AI systems grow increasingly complex, it becomes clear that this class of applications relies on a multi-layered architecture. Trying to chart such architecture reveals several security risks that could plague each layer. This article investigates the possible scenarios and offers actionable insights to secure each layer and combat such threats.
July 28th, 2025Vincenzo Ciancaglini, Marco Balduzzi, Salvatore Gariuolo, Rainer Vosseler…
Read article -
AI and Emerging TechnologiesDeepfake It ‘til You Make It: A Comprehensive View of the New AI Criminal Toolset
This report takes a comprehensive look at how deepfakes are used to support criminal business processes, what are the toolkits criminals are exploiting to power their deepfake creation, and what the deepfake underground looks like.
July 9th, 2025David Sancho, Salvatore Gariuolo, Vincenzo Ciancaglini
Read article -
AI and Emerging TechnologiesThe Road to Agentic AI: Defining a New Paradigm for Technology and Cybersecurity
Our latest research provides a framework for understanding agentic AI systems, outlines their core characteristics, and examines the security implications surrounding their use.
June 17th, 2025Salvatore Gariuolo, Vincenzo Ciancaglini
Read article