New PuzzleMask Attack Hides Malicious Prompts in Plain English to Bypass AI Guardrails
Security researchers have disclosed PuzzleMask, a prompt-obfuscation technique that can help malicious instructions slip past lightweight AI safety filters.
The method hides a policy-violating...
WordPress Launches AI-Powered Security Review to Block Malicious Plugin Updates
WordPress has introduced an automated, AI-powered security review process for every plugin release, aiming to stop vulnerable or malicious updates before delivering them to...
Hackers Turn Claude AI Agents Into Autonomous Tools for Exploitation, Data Theft and Malware Evasion
Threat actors are increasingly using Claude-based agentic workflows to automate reconnaissance, exploitation, credential theft, data exfiltration, and malware redevelopment.
Anthropic said it disrupted operations...
Hackers Exploit Critical Cisco FMC Flaws to Gain Root Access and Deploy Malware
Cisco Talos warns that threat actors are actively exploiting two vulnerabilities in Cisco Secure Firewall Management Center (FMC) Software, including a critical authentication-bypass flaw...
Critical Check Point VPN Flaws Let Unauthenticated Attackers Execute Remote Code
Check Point has disclosed two critical vulnerabilities in its VPN technology that could allow unauthenticated remote attackers to achieve remote code execution (RCE) under...