A high-severity OpenClaw flaw allows one-click remote code execution via token theft and WebSocket hijacking; patched in ...

January 2026 was a wake-up month for enterprise security teams. In a single week, CERT-In released three high-severity ...

The Model Context Protocol just got its first official extension, and it changes what AI assistants can do. MCP Apps lets tools return interactive user interfaces—dashboards, forms, visualizations, ...

The RedKitten campaign distributes lures designed to target people seeking information about missing persons or political ...

The rapid adoption of AI agents has exposed a structural security problem in the Model Context Protocol. Due to a lack of authentication, hundreds of MCP ...

A critical vm2 Node.js vulnerability (CVE-2026-22709, CVSS 9.8) allows sandbox escape via Promise handler bypass.

Two vulnerabilities in n8n’s sandbox mechanism could be exploited for remote code execution (RCE) on the host system.

Two vulnerabilities in the n8n workflow automation platform could allow attackers to fully compromise affected instances, access sensitive data, and execute arbitrary code on the underlying host.

To exploit the vulnerability, an attacker would need either system access or be able to convince a user to open a malicious ...

The AI bot OpenClaw, also known as Moltbot, can do a lot on user computers. A code smuggling vulnerability within it is ...

A hands-on test compared Visual Studio Code and Google Antigravity on generating and refining a simple dynamic Ticket Desk ...

Put rules at the capability boundary: Use policy engines, identity systems, and tool permissions to determine what the agent ...