AI worm

A security researcher demonstrated how Microsoft Copilot for Word can be exploited via a hidden JSON-formatted prompt embedded in white text on a white background within Word documents. The attack allows the prompt to propagate through document-sharing workflows as Copilot processes the hidden instructions, modifying documents and appending malicious prompts without user awareness. Microsoft's mitigations, including newer GPT models, have not fully resolved the vulnerability, which stems from an architectural weakness in LLM systems.

University of Toronto researchers have demonstrated an AI worm capable of targeting any online device, highlighting potential security vulnerabilities. The study showcases the ability of AI-driven malware to exploit connected systems without specific device limitations.