New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data
Adversa AI has disclosed a novel attack technique dubbed "Cryptographic Context Injection" that can cause xAI's Grok chatbot to exfiltrate a user's…
Tag: Gemini
AI ‘Mind Viruses’ Can Spread Between Agents via Persistent Prompt Files
Researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads, dubbed "mind viruses," can spread between AI agents through editable system…
AI Recommendation Poisoning: How ‘Ask AI’ Buttons Silently Alter LLM Memory
A new class of prompt injection attack, dubbed "AI Recommendation Poisoning," is spreading across commercial websites. It exploits pre-filled deep links in…
Chrome 149-151 Fix 1,442 Flaws, Surpassing Prior 23 Updates Combined
Google has patched a record 1,442 security vulnerabilities across Chrome versions 149, 150, and 151, surpassing the total number of flaws fixed…
CVE-2026-3545: Critical Sandbox Escape in Chrome Navigation
CVE-2026-3545 is a critical sandbox escape vulnerability in Chrome's Navigation component with a CVSS score of 9.6. It could be exploited to…
Gemini 3.5 Flash Cyber: Google’s AI Model for Vulnerability Discovery
A lightweight AI model fine-tuned to find, validate, and patch software vulnerabilities. In tests, it found 55 unique confirmed V8 issues and…
FakeGit Campaign Uses 7,600 GitHub Repositories to Spread SmartLoader Malware
Cybersecurity researchers have uncovered a large-scale campaign dubbed FakeGit, which leverages nearly 7,600 malicious GitHub repositories to distribute the SmartLoader malware. The…
EU Orders Google to Open Android Mic, Camera and Screen to Rival AI Assistants
The European Commission has issued binding specification decisions under the Digital Markets Act, ordering Google to grant rival AI assistants the same…
GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code
Researchers Abhishek Kumar and Carsten Maple have discovered a novel workflow-level jailbreak method that bypasses safety guardrails in GitHub Copilot. The study,…
AI Agent JADEPUFFER Exploits Langflow RCE to Automate Database Ransomware Attack
Security firm Sysdig has identified what it believes is the first ransomware attack fully orchestrated by an AI agent, dubbed JADEPUFFER. The…