A new attack technique could allow criminals to plant false information inside an AI agent’s long-term memory, potentially influencing decisions weeks or months later and creating a new security problem as businesses increasingly give AI systems greater autonomy. Memory Poisoning Researchers at US-based cyber security company Forcepoint have demonstrated how […]
Posted in News Also tagged AI, LiesThe 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 AI, Deceptive, SecurityAI agents running inside messaging apps can leak sensitive data through automatic link previews, researchers at AI security firm PromptArmor have warned, creating a zero-click data exfiltration risk. The flaw reportedly exploits indirect prompt injection. For example, an attacker tricks an agent into generating a malicious URL containing sensitive information, […]
Posted in News Also tagged AI, Chat, Data, LeaksMicrosoft has made AI-powered Agents in OneDrive generally available, allowing users to create persistent Copilot assistants that work across multiple documents rather than individual files. What Are AI Powered Agents? AI-powered agents in OneDrive are persistent Copilot assistants built from a user selected set of files, designed to understand and […]
Posted in News Also tagged AI, Microsoft, OneDriveMoltbook, a newly launched social platform designed for AI agents rather than humans, has drawn scrutiny after researchers exposed major security flaws and raised questions about how autonomous its AI activity really is. A Platform For ‘Agents’ Moltbook is presented as a social network designed specifically for AI agents, which […]
Posted in News Also tagged AI, Moltbook, Online
__________