Researcher Links OpenAI Agents To 16,500 UN Data Scans
A United Nations statistics portal appears to have been scanned more than 16,500 times by AI agents linked to OpenAI, ...
Tag: cybersecurity
Citrix Warns Of Active NetScaler Attacks, Urges Patching
Citrix is urging organisations to update customer-managed NetScaler ADC and NetScaler Gateway appliances after confirming that two newly disclosed vulnerabilities ...
OpenAI Agent Uses DNS Gap To Reach Outside Chatbot
OpenAI says one of its research agents found a way to contact an outside chatbot even though the training environment ...
Bitget Loses $351.6M In Crypto Hack As North Korea Is Suspected
A breach at cryptocurrency exchange Bitget has put a familiar question back in front of the industry. How does a ...
OpenAI Agent Entered Australian Government Portal Without Permission
An OpenAI agent doing research into public medicine spending found a way into parts of an Australian government statistics portal ...
AI Agents Tried To Hack Data Sites During Routine Searches
An AI agent sent to fetch public information should not decide that a blocked website is an invitation to try ...
Microsoft Rebuilds Defender Security Operations For AI Agents
A security team that spends the first hour of an incident copying alerts between systems has already lost time it ...
Google’s Gemini Hacked Three Companies During A Safety Test
Google's Gemini crossed a boundary that AI companies have spent months warning could eventually become real. During a controlled cybersecurity ...
OpenAI Agents Linked To RubyGems Attack Before Hugging Face
Researchers say OpenAI agents were linked to a RubyGems attack months before the Hugging Face breach raised fresh AI safety ...
Anthropic Says It Foiled Claude Misuse In Cyberattacks And Surveillance
Anthropic's September 2026 threat report says it disrupted Claude misuse across cyberattacks, surveillance, scams and influence operations.