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 vulnerability that researchers call CurXecute is present in almost all versions of the AI-powered code editor Cursor, and can be exploited to execute remote code with developer privileges. The ...

MCP, or Model Context Protocol, was proposed by Anthropic and is quickly becoming the industry’s standard interface between AI systems and traditional platforms. In a nutshell, it wants to be the AI ...

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.

Perplexity launches Bumblebee: How its new read-only dev scanner differs from Chainguard ...

OX Security confirmed arbitrary command execution on six live platforms and estimates 200,000 MCP servers are exposed. Here's how to audit your deployments.

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 ...