The mcp-remote utility contains a critical OS command injection vulnerability that could allow unauthenticated attackers to execute arbitrary system commands.

This vulnerability is an OS command injection flaw occurring when the application parses input from an authorization_endpoint response URL. The vulnerability is triggered during the connection phase to an untrusted server, allowing an attacker to inject and execute system-level commands.

The CVSS score of 9.6 highlights the extreme risk of complete system compromise. An attacker successfully exploiting this flaw could gain full control of the host machine, leading to total data exfiltration, installation of persistent backdoors, and significant operational disruption.

Immediate Action: Update the mcp-remote application to the latest version provided by the vendor to remediate the command injection vector.

Proactive Monitoring: Audit logs for unexpected process execution or suspicious shell commands originating from the mcp-remote service.

Compensating Controls: Ensure the application is running with the principle of least privilege, minimizing the impact of potential command execution by limiting the user's system permissions.

Public Exploit Available: Not specified

The severity of this command injection vulnerability necessitates an immediate audit of all systems utilizing mcp-remote. Organizations should prioritize patching to the latest secure version to mitigate the risk of remote system take-over.