CVE-2026-100596

8.8 HIGHpublic exploit available

Published 2026-09-26 · Updated 2026-09-28

AI risk analysis

Summary: OpenClaw versions before 2026.7.1 allow non-owner users to execute arbitrary stdio MCP commands with process privileges, leading to potential host compromise.
Exploitability: Exploitation is relatively straightforward as it requires non-owner user access to the /mcp set and /mcp unset commands.
Blast radius: If exploited, this flaw could result in significant host confidentiality, integrity, and availability issues.
Detection: No reliable host or network indicator is derivable from the published description.
Prioritized remediation: Upgrade to OpenClaw 2026.7.1 or later.

rceprivilege-escalationconfigurationmcp

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

OpenClaw versions before 2026.7.1 fail to properly authorize non-owner users executing MCP configuration changes through /mcp set and /mcp unset commands. Attackers can persist arbitrary stdio MCP commands that execute with OpenClaw process privileges when configuration loads, compromising host confidentiality, integrity, and availability.

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Weaknesses

CWE-862

Public exploit & PoC references

https://github.com/openclaw/openclaw/security/advisories/GHSA-wwx7-573h-pqwc

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.