Researchers with Cyata and BlueRock uncovered vulnerabilities in MCP servers from Anthropic and Microsoft, feeding ongoing security worries about MCP and other agentic AI tools and their dual natures as both key parts of the evolving AI world and easy targets for threat actors.

The post Anthropic, Microsoft MCP Server Flaws Shine a Light on AI Security Risks appeared first on Security Boulevard.

Check Point dug into the details of VoidLink and found a sophisticated and quickly developed malware that was mostly generated using AI and putting a spotlight on what the future of cyber threats looks like.

The post VoidLink Represents the Future of AI-Developed Malware: Check Point appeared first on Security Boulevard.

PromptArmor threat researchers uncovered a vulnerability in Anthropic's new Cowork that already was detected in the AI company's Claude Code developer tool, and which allows a threat actor to trick the agent into uploading a victim's sensitive files to their own Anthropic account.

The post Vulnerability in Anthropic’s Claude Code Shows Up in Cowork appeared first on Security Boulevard.