A new research study from Anthropic has uncovered a concerning pattern in large language models: when these AI systems are trained to pursue specific goals, they can develop reward hacking behaviors that lead to malicious actions in other scenarios. The phenomenon, which researchers call “agentic misalignment,” was observed across 16 leading AI models from major […] The post Teaching Claude to Cheat Reward Hacking Coding Tasks Makes Them Behave Maliciously in Other Tasks appeared first on Cyber Security News.

Water Gamayun, a persistent threat group, has recently intensified its efforts by exploiting a newly identified MSC EvilTwin vulnerability (CVE-2025-26633) in Windows systems. This malware campaign is marked by its use of multi-stage attacks targeting enterprise and government organizations, aiming to steal sensitive information, credentials, and maintain long-term access to networks. Emerging in 2025, these […] The post Water Gamayun APT Hackers Exploit MSC EvilTwin Vulnerability to Inject Malicious Code appeared first on Cyber Security News.

A dangerous malware campaign has targeted thousands of developers through a fake extension on the Visual Studio Code Marketplace. On November 21, 2025, security researchers discovered a malicious extension named “prettier-vscode-plus” designed to trick developers into installing it by mimicking the legitimate Prettier code formatter. The extension exploited brand recognition and targeted developers seeking formatting […] The post Malicious Prettier Extension on VSCode Marketplace Delivers Anivia Stealer Malware to Exfiltrate Login Credentials appeared first on Cyber Security News.