Critical Vulnerability in Anthropic's MCP Exposes Developer Machines to Remote Exploits

Cybersecurity researchers have discovered a critical security vulnerability in artificial intelligence (AI) company Anthropic's Model Context Protocol (MCP) Inspector project that could result in remote code execution (RCE) and allow an attacker to gain complete access to the hosts. The vulnerability, tracked as CVE-2025-49596, carries a CVSS score of 9.4 out of a maximum of 10.0. "This is one

Posted from: Click here for the full article.

留言

此網誌的熱門文章

CISA Adds NAKIVO Vulnerability to KEV Catalog Amid Active Exploitation

Microsoft Expands Free Logging Capabilities for all U.S. Federal Agencies

OttoKit WordPress Plugin Admin Creation Vulnerability Under Active Exploitation