AI vulnerability Archives

AI Chronicle|1,200+ AI Articles|Daily AI News|3 Products in ShopFree Newsletter →

Your daily source for AI news, tools reviews, and practical guides to artificial intelligence

Critical Vulnerability Found in Anthropic’s Claude Cowork AI Just Days After Launch

ChronoJanuary 18, 202604 mins

Security researchers have uncovered a serious flaw in Anthropic’s newly released agentic AI system Claude Cowork, enabling attackers to steal confidential user files through hidden prompt injections without any human authorization.

Study Reveals Poetry as a Potent Bypass for AI Security Filters in Large Language Models

ChronoNovember 29, 202504 mins

A recent study uncovers a critical vulnerability in large language models where malicious prompts framed as poetry evade security measures with alarming success, raising concerns about AI safety and alignment.