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 ...
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 ...
The Model Context Protocol (MCP) has emerged as a “USB-C port for AI applications” that standardizes how AI systems interact with external data sources and tools. While MCP revolutionizes AI integration by enabling seamless connections between AI models and diverse services, this powerful capability introduces significant MCP defense and security challenges ...
The Model Context Protocol (MCP), introduced by Anthropic in November 2024, has rapidly emerged as the “USB-C port for AI Agents and applications” — revolutionizing how AI systems interact with external tools and data sources. This protocol standardizes the connection between Large Language Models (LLMs) and various services, enabling powerful ...
On 30 June 2025, security researchers Ian Carroll and Sam Curry opened McDonald’s recruiting site, clicked a tiny “Paradox team members” link, typed the universal joke password 123456, and found themselves inside the admin console of McHire—the AI-driven chatbot platform that screens applicants for about 90% of McDonald’s 40,000+ restaurants ...
Executive Summary: “The Asana MCP incident exposed 1,000 organizations’ data through a single line of code, proving that when AI meets enterprise SaaS, yesterday’s security playbook is obsolete. This isn’t about one vendor’s mistake – it’s about an industry racing to deploy AI without understanding the fundamentally different threat model ...
As AI systems shift from passive responders to autonomous agents capable of planning, tool use, and long-term memory, they introduce new security challenges that traditional red teaming methods fail to address. To explore the current state of Agentic AI Red Teaming, we interviewed four leading language models—ChatGPT, Claude, Grok, and ...
Why MCP Security Issues Are Growing — and Why You Should Care The Model Context Protocol (MCP) is rapidly emerging as the backbone of autonomous agent communication—akin to what TCP/IP is for the internet. But with its rising adoption comes a growing wave of exploits. As researchers and attackers alike ...
Prompt injection remains one of the most dangerous and poorly understood threats in AI security. To assess how today’s large language models (LLMs) handle Prompt Injection risks, we interviewed ChatGPT, Claude, Grok, and Deepseek. We asked each of them 11 expert-level questions covering real-world attacks, defense strategies, and future readiness. ...
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), [...]
