A critical authorization bypass in OpenClaw allows authenticated attackers to execute arbitrary commands with process-level privileges, resulting in a total compromise of host confidentiality, integrity, and availability.

This is a missing authorization flaw (CWE-862) occurring within the MCP configuration command set. Any authenticated user can leverage the /mcp set and /mcp unset commands to inject malicious stdio commands that execute with the privileges of the OpenClaw process.

The ability for a standard user to execute arbitrary commands with process privileges represents a severe security failure. Successful exploitation leads to a complete compromise of the host system, potentially allowing for lateral movement, data exfiltration, or total system disruption. Given the CVSS score of 8.8, this vulnerability poses a high risk to business operations and data security.

Immediate Action: Update the OpenClaw software to version 2026.7.1 or later immediately to incorporate the required authorization checks.

Proactive Monitoring: Review application and system access logs for anomalous usage of the /mcp command and monitor for unexpected child processes spawning from the OpenClaw service.

Compensating Controls: Implement strict network segmentation and restrict access to the OpenClaw interface to trusted internal users only, as the vulnerability requires existing authenticated access.

Public Exploit Available: No (exploit_available: false)

This vulnerability presents a significant risk due to the potential for full system compromise from a low-privileged account. Security teams should prioritize patching OpenClaw to version 2026.7.1 across all environments without delay. If immediate patching is not feasible, restrict access to the application to the minimum required users and monitor logs for any suspicious configuration changes.