Check Point researchers uncovered a remote code execution bug in popular vibe-coding AI tool Cursor that could allow an attacker to poison developer environments by secretly modifying a previously ...

A new proof-of-concept attack shows that malicious Model Context Protocol servers can inject JavaScript into Cursor’s browser — and potentially leverage the IDE’s privileges to perform system tasks.

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

The Browser MCP (Model Context Protocol) server, when paired with Cursor, provides a comprehensive platform for automating browser tasks and testing web applications. By combining browser navigation, ...

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

Every secure API draws a line between code and data. HTTP separates headers from bodies. SQL has prepared statements. Even email distinguishes the envelope from the message. The Model Context Protocol ...

A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into ...

SAN FRANCISCO, March 20, 2026 /PRNewswire/ -- WordPress.com, Automattic's hosted website platform built on the open source WordPress software, today announced the launch of new write capabilities for ...

The Model Context Protocol (MCP) enables AI agents to interact with external tools across hybrid environments but introduces critical security vulnerabilities, including identity theft, data leakage, ...

What if you could replicate the design of any website or transform intricate Figma files into functional code with just a few clicks? It might sound like a developer’s pipe dream, but thanks to ...