AI Security

Researchers Reveal Google Gemini AI Flaws Enabling Prompt Injection and Cloud Exploits

Cybersecurity researchers have disclosed a trio of now-patched vulnerabilities, collectively called the Gemini Trifecta, that impacted Google’s Gemini AI suite. If exploited, these flaws could have exposed users to privacy breaches and data theft, by turning AI features into attack vectors, rather than just targets. The findings underscore a worrying trend, where sophisticated threat actors, […]

Researchers Reveal Google Gemini AI Flaws Enabling Prompt Injection and Cloud Exploits Read More »

EvilAI Malware Masquerades as AI Tools to Infiltrate Global Organizations

Threat actors are exploiting the popularity of artificial intelligence (AI) by embedding malware into fake productivity and AI-enhanced tools, according to a recent Trend Micro report. This campaign, known as EvilAI, is targeting organizations worldwide across regions such as Europe, the Americas, and the Asia, Middle East, and Africa (AMEA) region. Global Impact and Targeted

EvilAI Malware Masquerades as AI Tools to Infiltrate Global Organizations Read More »

GPT-5 Jailbreak and Zero-Click AI Agent Exploits Threaten Cloud and IoT Security

Cybersecurity researchers have revealed a new jailbreak method targeting OpenAI’s GPT-5 language model, enabling it to bypass ethical safeguards and produce harmful instructions. The method, developed by NeuralTrust, combines a known exploit called Echo Chamber with a narrative-driven approach to manipulate the AI’s responses. By seeding the conversation with subtle cues and reinforcing them through storytelling, attackers

GPT-5 Jailbreak and Zero-Click AI Agent Exploits Threaten Cloud and IoT Security Read More »