CVE-2026-7064
A flaw has been found in AgentDeskAI browser-tools-mcp up to 1.2.0. This issue affects some unknown processing of the file browser-tools-server/browser-connector.ts. Executing a manipulation can lead to os command injection. The attack may be performed from remote. The exploit has been published and may be used. The project was informed of the problem early through an issue report but has not responded yet.
Ver en NVDAnálisis
This is a remote OS command injection in a Model Context Protocol (MCP) server for AI agents. While the vulnerability is severe and an exploit is public, the software is a niche utility within the emerging AI agent ecosystem and does not yet have the widespread deployment required for a community-wide alert.
Severidad
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:LCWE-77CWE-78EPSS
Descripción técnica
A flaw has been found in AgentDeskAI browser-tools-mcp up to 1.2.0. This issue affects some unknown processing of the file browser-tools-server/browser-connector.ts. Executing a manipulation can lead to os command injection. The attack may be performed from remote. The exploit has been published and may be used. The project was informed of the problem early through an issue report but has not responded yet.