MCP is becoming ubiquitous in agentic AI toolchains, but it places a non-deterministic LLM at the center of security-critical decision-making. The CoSAI white paper reveals more than 40 MCP threats that most organizations aren’t addressing and proposes controls and mitigations.
Cascading failures in agentic AI: the definitive OWASP ASI08 security guide A Comprehensive Technical Reference for Security Professionals, Architects, and Risk Managers Table of contents Introduction: understanding cascading failures in agentic AI Why cascade prevention matters for agentic AI security Anatomy of agentic AI cascading failures Temporal patterns of cascading ...
AI Reasoning Leakage Vulnerability: Self-betrayal attack UAE MBZUAI G42 K2 Think Executive Summary A critical vulnerability has been identified in advanced reasoning system of just released latest reasoning model by UAE’s Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) in collaboration with G42 where the model’s internal thought process inadvertently exposes ...
As AI systems evolve from passive responders to autonomous agents equipped with planning, memory, and tool use, the Model Context Protocol (MCP) becomes a central architectural layer — and a new security frontier. Yet traditional red teaming approaches are ill-equipped to test how MCP-enabled agents interact, delegate, and reason across ...
In August 2025, Lenovo quietly patched a critical vulnerability in its AI chatbot “Lena” that could have allowed attackers to steal session cookies and potentially compromise customer support systems through a single 400-character prompt—highlighting a new class of AI-driven security threats that most organizations are unprepared to defend against. The ...
The rapid deployment of generative AI systems across critical infrastructure has created an unprecedented security challenge: how do we effectively test and secure systems that can generate content, make decisions, and interact with users in ways we never fully anticipated — even with AI Red Teaming in place? A groundbreaking ...
Executive Summary for CISO Security researchers from Adversa AI discovered that ChatGPT 5 have a fatal flaw: they can route your requests to cheaper, less secure models to save money. Attackers can exploit this to bypass AI security and safety measures with just a few words. What Is PROMISQROUTE? When ...
NOTE: This Blurpring should not be viewed as an alternative to in-depth AI Red Teaming done by professionals but rather a first step to understand AI Risks Posture. In an era where generative AI systems are becoming deeply embedded in our digital infrastructure, the UNESCO Red Teaming Playbook emerges as ...
Introduction. When AI Becomes the Attack Vector In the world of AI red teaming, we often ask ourselves: “What’s the worst that could happen?” On July 2025, we got our answer—and it wasn’t from a sophisticated nation-state actor or a zero-day exploit. It came from a single frustrated hacker who ...
Introducing Universal LLM Jailbreak approach. Subscribe for the latest AI Jailbreaks, Attacks and Vulnerabilities If you want more news and valuable insights on a weekly and even daily basis, follow our LinkedIn to join a community of other experts discussing the latest news. In the world of artificial intelligence (AI), [...]
