OpenAI has issued a warning regarding Astra, an upcoming artificial intelligence model, which may be close to a threshold of cybersecurity capabilities…
Tag: AI Security
Russian-Speaking Hackers Used Cursor AI Agent to Target Seven Companies
Russian-speaking cybercriminals from the emerging Aur0ra ransomware group used Cursor’s AI coding agent to assist attacks against at least seven companies…
OpenAI Reveals AI Agents Built Unauthorized Message Board That Contributed to Hugging Face Breach
OpenAI has revealed that an unauthorized communication system created by its own AI agents played a key role in an incident that led to parts of Hugging…
OpenAI Is Pulling Its AI Models From Cursor Following SpaceX Acquisition
OpenAI is pulling its AI models from Cursor following SpaceX’s acquisition of the AI coding assistant, notifying SpaceX that it will wind down the…
The Cybersecurity Apocalypse Is Coming in ‘Months,’ AI Giants Warn
Plus: Hackers target over 100 US water systems, ICE puts in an order for robot dogs, and you’ll never guess what “MrChildPorn” was arrested for.
700 AI Agents Secretly Coordinated to Hack Hugging Face After Breaking Their Isolation
A large group of AI agents reportedly bypassed their intended isolation, created a covert communication channel, and coordinated an attack on Hugging Face…
The Balance Of Healthcare Research Potential And Privacy In The Age Of AI
There’s no question that AI has transformed healthcare research and completely changed the trajectory of the healthcare industry. What would have taken…
Anthropic MHS Lets AI Agents Control Machines, Raising Security Questions
Anthropic’s Model Hardware Standard lets AI agents control physical equipment, raising questions about permissions, monitoring and operational security.
Hackers Target AI Infrastructure With RCE, Prompt Injection and API Key Theft
Hackers are actively probing AI systems, turning exposed gateways and agent tools into routes for remote code execution, credential theft, and…
700 AI Agents Helped Carry Out Hugging Face Attack
An overarching number of 700 artificial intelligence agents participated in a coordinated attack against Hugging Face after models running inside OpenAI’s…
Ransomware Gang Claims AI Can Analyze 700GB of Stolen Data Every Hour
TITAN ransomware is pairing file encryption with an ambitious claim: artificial intelligence that can sort through 700GB of stolen corporate data every…
Frontier AI tipping the scales toward cyber adversaries
Researchers at Palo Alto Networks’ Unit 42 warn that threat actors are already using AI to accelerate cyberattacks beyond the abilities of modern defenses.
AI Agent Hacks Gym Booking System
An AI agent designed to help with everyday tasks has ended up exposing a serious security flaw in a gym booking system. According to a report cited by…
OpenAI Says Reward Hacking Fueled AI Agents’ Hugging Face Cyberattack
OpenAI has disclosed that reward hacking played a central role in an AI-driven cyberattack targeting Hugging Face, revealing that signs of misaligned…
Russian-Speaking Hackers Used Cursor AI in Attacks on Seven Companies, Report Says
Russian-speaking hackers used Cursor AI during attacks on corporate networks, reportedly speeding reconnaissance, VPN access and exploitation attempts.
Attackers Exploit MCP RCE, Blind Prompt Injection and Memory Credential Theft Against AI Infrastructure
Attackers are increasingly treating AI infrastructure as a high-value cloud entry point, exploiting exposed Model Context Protocol (MCP) services, agent…
700 AI Agents Linked to Hugging Face Security Breach
Around 700 AI agents created by OpenAI participated in the breach of Hugging Face during a cybersecurity evaluation, according to an independent…
AI Doesn’t Mean the End of Mathematics—at Least Not Yet
This essay was written with Kasra Rafi, and originally appeared in The Guardian. Earlier this month, about 40 top mathematicians gathered at OpenAI’s…
The AI agent swarm that attacked Hugging Face is a warning for the future
An army of AI agents was responsible for the Hugging Face incident. What does it mean for the future of AI?
Researchers Execute Code Inside Fortune 500 Companies via AI Agent llms.txt Files
Security researchers have shown that AI coding agents can be manipulated into installing attacker-controlled packages by following instructions found in…