Anthropic’s AI coding assistant, Claude Code, has been found to contain a critical security vulnerability that silently bypasses user-configured safety controls, exposing developers to potential data theft and command execution attacks. The flaw allows malicious actors to evade “deny rules,” a key security feature designed to block dangerous commands such as curl, rm, or data […] The post Critical Claude Code Flaw Ignores User-Defined Security Rules appeared first on Cyber Security News.