Critical RCE Vulnerability in Anthropic's AI Supply Chain Protocol

OX Security has identified a significant RCE-by-Design vulnerability in Anthropic’s Model Context Protocol (MCP), which poses a critical risk to organizations utilizing AI agents. This flaw has led to over 30 responsible disclosures and more than 10 High/Critical CVEs. The vulnerability stems from architectural choices in the MCP, making it a systemic issue rather than a simple patchable flaw. The ongoing risk affects any organization that integrates AI into their operations, emphasizing the need for enhanced Software Supply Chain Security. Despite efforts to address downstream impacts, the root cause remains unpatched at the protocol level. Security leaders are urged to adopt a 'Secure by Design' approach to mitigate these risks. The current status indicates that while patches have been issued, the fundamental vulnerability persists.

Key Points: • A critical RCE vulnerability in Anthropic's MCP threatens AI supply chains. • Over 30 responsible disclosures and 10+ High/Critical CVEs have been reported. • Organizations are advised to prioritize Software Supply Chain Security.