Browsing Tag
Artificial Intelligence
258 posts
New GeminiJack 0-Click Flaw in Gemini AI Exposed Users to Data Leaks
Google AI systems (Gemini Enterprise) had a critical 'GeminiJack' security flaw allowing attackers to steal Gmail, Docs, and Calendar data with no clicks.
PromptPwnd Vulnerability Exposes AI driven build systems to Data Theft
Aikido Security exposes a new AI prompt injection flaw in GitHub/GitLab pipelines, letting attackers steal secrets. Major companies affected.
HashJack Attack Uses URL ‘#’ to Control AI Browser Behavior
Cybersecurity firm Cato Networks reveals HashJack, a new AI browser vulnerability using the '#' symbol to hide malicious commands. Microsoft and Perplexity fixed the flaw, but Google's Gemini remains at risk.
Cronos Kicks Off $42K Global Hackathon Focused on AI-Powered On-Chain Payments
Cronos launches x402 PayTech Hackathon with $42K prize pool to drive AI-powered on-chain payments using agent tech and Crypto.com tools.
OpenAI API User Data Exposed in Mixpanel Breach, ChatGPT Unaffected
OpenAI confirmed a third-party data breach via Mixpanel, exposing limited API user metadata like names, emails and browser…
Elena Lazar: Failures are Inevitable – Reliability is a Choice
Reliability engineer on why resilience must be designed, not patched, and how decades of global experience taught her to turn outages into insights.
Can We Trust AI with Our Cybersecurity? The Growing Importance of AI Security
Artificial intelligence (AI) helps us in doing small and big things that are important in our daily lives.…
Comet Browser Flaw Lets Hidden API Run Commands on Users’ Devices
SquareX warns Perplexity's Comet AI browser contains a hidden MCP API that bypasses security, allowing attackers to install malware and seize full device control.
Cline Bot AI Agent Vulnerable to Data Theft and Code Execution
Mindgard reveals 4 critical security flaws in the popular Cline Bot AI coding agent. Learn how prompt injection can hijack the tool for API key theft and remote code execution.
EchoGram Flaw Bypasses Guardrails in Major LLMs
HiddenLayer reveals the EchoGram vulnerability, which bypasses safety guardrails on GPT-5.1 and other major LLMs, giving security teams just a 3-month head start.