The security defects could be exploited for remote code execution, OS command injection, and WAF detection bypass.

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...

Two newly discovered macOS threats are designed to harvest developer credentials and cloud access as attackers focus on ...

Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture ...

Researchers say a prompt injection bug in Google's Antigravity AI coding tool could have let attackers run commands, despite ...

A design choice in the MCP SDKs allows remote code execution across the AI supply chain.

A prompt injection flaw in Google’s Antigravity IDE turns a file search tool into a remote code execution vector, bypassing ...

The prompt-injection issue in the agentic AI product for filesystem operations was a sanitization issue that allowed for ...

A growing range of native macOS features are being repurposed by attackers to execute code, move laterally and evade ...

In the news release, Bybit Uncovers AI-Assisted macOS Malware Campaign Targeting Users Searching for Claude Code, issued 21-Apr-2026 by Bybit over PR Newswire, we are advised by the company that the ...

Hackers are abusing Microsoft Teams chats to impersonate IT support, gain remote access, move laterally, and steal company ...

Serial-to-IP converters are affected by potentially serious vulnerabilities that can expose OT and healthcare systems to ...