Ransomware Affiliate Used AI Coding Tool Cursor to Plan Attacks on 20+ Companies Across 9 Countries
An exposed staging server has given researchers an unusually detailed look at how a Russian-speaking Aurora ransomware affiliate used the AI coding assistant Cursor to help plan and...
Grok AI Chatbot Tricked Into Leaking Private Chats Through Encrypted Prompt Injection
Security researchers at Adversa AI found a zero-click flaw in xAI's Grok that hides malicious instructions inside encrypted text to steal names, locations, and chat history. The attack...
Critical MLflow Flaw Lets Attackers Steal Cloud Credentials via Webhook Redirects
A critical server-side request forgery flaw in MLflow, tracked as CVE-2026-64849 with a 9.3 CVSS score, lets unauthenticated attackers abuse the platform's webhook-testing endpoint to reach cloud metadata...
Security Leaders Warn the ‘Agentic Attacker’ Has Arrived After AI Models Reportedly Breached Hugging Face on Their Own
An incident in which autonomous OpenAI models allegedly broke out of a sandboxed test environment and gained remote code execution on Hugging Face's infrastructure — carrying out more...
How a Rogue Prompt Could Turn Microsoft Copilot Into a $250,000 Wire Fraud Accomplice
A proof-of-concept from Barracuda researchers shows how attackers could weaponize Microsoft Copilot itself to escalate a single compromised inbox into full CEO account takeover and a quarter-million-dollar wire...
Claude Broke Out of a Sandboxed Security Test and Hit Three Real Companies, Anthropic Admits
Anthropic says a review of 141,000 evaluation transcripts turned up three cases where Claude models, told they were operating in an isolated capture-the-flag simulation, instead reached the live...
Hugging Face Breach Reveals a New Front: AI Agents Attacking, AI Agents Defending
Hugging Face has confirmed a production infrastructure intrusion driven by an autonomous AI agent, exploiting two flaws in its dataset processing pipeline. The company's own AI-based forensic analysis...
Inside NadMesh: The Shodan-Powered Botnet Hunting Exposed AI Servers
Researchers at XLab have identified NadMesh, a Go-based botnet that uses Shodan to hunt down exposed AI and MCP infrastructure before hijacking it with more than 20 exploitation...