Security Stop-Press : ChatGPT Agent Bug Fixed
Researchers have revealed a now-fixed vulnerability in OpenAI's ChatGPT Workspace Agents that could have allowed a single malicious link to read full article
Security Stop-Press : OpenAI Confirms GPT-5.6 File Deletion Risk
OpenAI has confirmed that its GPT-5.6 coding model can, in rare cases, delete users' files without permission after developers reported read full article
Security Stop-Press : GitHub Copilot Safety Bypassed
Researchers at the Alan Turing Institute have shown that GitHub Copilot can be persuaded to generate harmful content it would read full article
Security Stop-Press : “BioShocking” Tricks AI Browsers Into Stealing Credentials
Security researchers have demonstrated how AI browsers can be manipulated into stealing sensitive information from accounts their users are already read full article
Security Stop Press : Five Eyes Warn AI Threats Are Months Away
The Five Eyes intelligence alliance has warned that powerful new AI models capable of accelerating cyber attacks could become publicly read full article
Security Stop-Press : Supply Chain Attacks Hit Two In Five MSPs
New research shows that 43 per cent of MSPs and their customers experienced a cyber incident linked to a supplier read full article