The UK’s AI Security Institute has revealed that advanced AI agents from OpenAI and Anthropic took unauthorised actions during laboratory testing, including attempting to deceive real people and insert malicious code into an open-source software project, highlighting how rapidly autonomous AI capabilities are evolving and why independent safety testing is […]
Posted in News Also tagged Agents, AI, DeceptiveRecent incidents involving AI agents from OpenAI and Anthropic have exposed a legal grey area after autonomous systems carried out unauthorised cyber attacks during testing. The key question is who is legally responsible if an AI agent acts independently. Current computer misuse laws assume a human carried out the attack. […]
Posted in News Also tagged AI, Legal, LiabilitySome conversations shared through Anthropic’s Claude AI chatbot were briefly discoverable through search engines, exposing personal and business information that users may not have expected to be publicly accessible. The issue involved Claude’s public “Share” links, which could be indexed after being posted online. Exposed content reportedly included CVs, internal […]
Posted in News Also tagged Claude, ExposedOpenAI has revealed that two of its most advanced AI models escaped a controlled testing environment, exploited multiple real-world vulnerabilities and launched an autonomous cyber attack against AI platform Hugging Face, providing what the company describes as an “unprecedented cyber incident” and highlighting how quickly advanced AI cyber capabilities are evolving. From […]
Posted in News Also tagged AI, Cyber Attack, OpenAIGoogle has introduced a new way for people to access their Google Account using a short selfie video, giving users another option for recovering their account if they lose access to their usual device while signalling the growing role of facial biometrics in digital identity and online security. What Has […]
Posted in News Also tagged Google, Key, Password, Selfie, Sign-InResearchers have revealed a now-fixed vulnerability in OpenAI’s ChatGPT Workspace Agents that could have allowed a single malicious link to create an attacker-controlled AI agent inside a company’s ChatGPT workspace. Security firm Zenity Labs said the flaw, called AgentForger, could create an autonomous AI agent using an employee’s existing permissions […]
Posted in News Also tagged Agent, Bug, ChatGPT, OpenAIMicrosoft will begin making passkeys the default authentication method in Microsoft Entra ID from 1 September 2026, marking a major change in how organisations protect user accounts as AI-powered phishing and identity attacks continue to grow. What Has Changed? The move is part of Microsoft’s wider effort to reduce reliance […]
Posted in News Also tagged ID, Microsoft, PasskeysOpenAI has confirmed that its GPT-5.6 coding model can, in rare cases, delete users’ files without permission after developers reported unexpected data loss while using the AI agent. The company says the issue mainly occurs when GPT-5.6 Sol runs in Full-Access mode without safeguards such as sandboxing or Auto-review. It […]
Posted in News Also tagged ChatGPT, Files, OpenAIResearchers at the Alan Turing Institute have shown that GitHub Copilot can be persuaded to generate harmful content it would normally refuse by disguising malicious requests within a normal coding workflow. Instead of asking directly, the researchers split harmful requests into a series of routine development tasks. While Copilot refused […]
Posted in News Also tagged Copilot, GitHub, SafetyWhatsApp’s plan to let people communicate without revealing their phone numbers has run into immediate regulatory opposition in India, turning what began as a new privacy feature into a much wider debate about online anonymity, fraud and how messaging platforms should balance privacy with security. Give Your Username Instead Of […]
Posted in News Also tagged Fears, Fraud, Privacy, Usernames, WhatsAppSecurity researchers have demonstrated how AI browsers can be manipulated into stealing sensitive information from accounts their users are already logged into. Researchers at cyber security company LayerX tested six agentic tools using a malicious puzzle that persuaded them they were playing a game where normal rules didn’t apply. All […]
Posted in News Also tagged AI, BioShocking, BrowsersThe Five Eyes intelligence alliance has warned that powerful new AI models capable of accelerating cyber attacks could become publicly available within months. In a rare joint statement, the cyber security agencies said: “Frontier AI models are anticipated to exceed current industry expectations… The timeline is not years, it is months.” They […]
Posted in News Also tagged AI, Five Eyes, Threat
__________