Malicious Hugging Face Models Could Trigger Remote Code Execution

A flaw in Hugging Face Transformers could allow malicious AI models to execute code, exposing credentials and highlighting AI supply chain risks.

Red teamers turned Claude Desktop into a double agent to do their evil bidding

EXCLUSIVE Pentera Labs’ red teamers compromised a developer’s AI agent via his Claude Desktop app and ultimately turned that access into full remote code execution on the devs ...
CSOonline

RCE by design: MCP architectural choice haunts AI agent ecosystem

Unsafe defaults in MCP configs open servers to possible remote code execution, as evidenced by several commercial services and open-source projects. AI agent building tools enable users to configure ...
Bleeping Computer

PromptSpy is the first known Android malware to use generative AI at runtime

Researchers have discovered the first known Android malware to use generative AI in its execution flow, using Google’s Gemini model to adapt its persistence across different devices. In a report today ...
TechSpot

Unwanted AI upgrade to Windows Notepad created a serious security flaw

The big picture: Microsoft released its latest Patch Tuesday update this week with 59 hotfixes across Windows, Microsoft Office, Azure, and core system components. The update includes patches for six ...

Microsoft’s multi-agent AI system tops Anthropic’s Mythos on cybersecurity benchmark

Microsoft's new vulnerability-scanning system, codenamed MDASH, scored 88.45% on the CyberGym benchmark, surpassing single-model systems from Anthropic and OpenAI by using more than 100 specialized AI ...