Russian-speaking hackers used Cursor AI during attacks on corporate networks, reportedly speeding reconnaissance, VPN access and exploitation attempts.
Tag: AI Security
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…
Teaching AI to Reason Through Detection Triage
This post has no text preview — click the link below to read the original article. This article has been indexed from Blog Read the original article: Teaching AI to Reason Through Detection Triage
Threat Actors Abuse Cursor Agent AI to Assist Ransomware Operations
Aurora ransomware operators are abusing SpaceX’s Cursor Agent AI tool to conduct tasks such as reconnaissance and exploitation activities
TITAN RaaS Uses AI for Data Classification, Regulatory Analysis and Automated Ransom Calculation
A newly emerged ransomware-as-a-service operation named TITAN is advertising an AI-driven extortion platform that it claims can autonomously classify…
AI IR Overlay – Incident Response Specification for AI Agents
AI IR Overlay specifies containment for agents using valid credentials, with a working kill-switch contract and an admitted gap when no SOC is staffed.
What 90 days and a small budget can buy in AI agent security
In this interview with Help Net Security, Prasad Tharippala, Field CISO at Versa, explains what organizations miss when they run open-weight models in…
100+ Tech and Security Organizations Call for Global Cyber Defense Surge Against AI Attacks
More than 100 technology, cybersecurity, and financial-services organizations have joined OpenAI in an open letter urging a global surge in cyber defense…
OpenAI Says Reward Hacking Drove AI Agents to Exploit Zero-Days and Breach Hugging Face
OpenAI on Wednesday revealed that reward hacking was a key driver behind the artificial intelligence (AI)-powered hack of Hugging Face last month, adding…
AI girlfriend review site’s secrets were exposed to the world for three weeks
Even testing and staging sites need protection from prying eyes
Expanding AI Benchmarks in Cybersecurity Beyond Vulnerability Discovery
This post has no text preview — click the link below to read the original article. This article has been indexed from Blog Read the original article: Expanding AI Benchmarks in Cybersecurity Beyond Vulnerability Discovery
GitLab Fixes Claude AI Agent Flaw That Could Execute Arbitrary Commands in CI Pipeline
GitLab has released security updates to fix a high-severity vulnerability in its Duo Claude AI agent that could allow authenticated developers to execute…
OpenAI Bans Russian ChatGPT Accounts Used in Covert Influence Campaign
OpenAI banned Russian ChatGPT accounts tied to a covert influence campaign involving copied research, fake attribution and coordinated social posts.
Cisco Report Shows How AI Agents Are Changing Cybersecurity Jobs
Cisco research shows how AI agents are reshaping cybersecurity roles and skills.
Ring’s New TAKE Encryption Deletes Video Keys Without Giving Up AI Features
Ring’s new TAKE encryption limits video-key retention while keeping cloud AI features, Ring Verify, and optional end-to-end encryption in play.
Here’s all the times AI has gone rogue and hacked other companies
A recap of all the incidents involving LLMs made by Anthropic, Meta, and OpenAI, which went rogue and attacked real companies and individuals on the…