Executive brief
OpenClaw, a tool used for managing automated tasks and command dispatch, contains a security flaw in how it handles 'skill' commands. This vulnerability allows users with low-level access to bypass security policies and perform actions they are not authorized to do. If exploited, an attacker could execute unauthorized commands or modify settings, potentially leading to unauthorized data access or system changes.
Technical details
An authorization bypass vulnerability (CWE-863) exists in OpenClaw's skill command dispatch mechanism. The flaw allows lower-trust callers or specific input paths to circumvent effective tool policy restrictions. An attacker with low privileges can exploit this over a network to execute or persist actions beyond their intended authorization level, provided the affected feature is enabled and reachable. The vulnerability does not affect the trusted-operator model for authenticated Gateway operators or installed plugins, but rather focuses on the command dispatch boundary. The issue is resolved in version 2026.5.18.
Affected products
- OpenClaw OpenClaw < 2026.5.18
Timeline
- 2026-06-30: advisory: GitHub Security Advisory published
- 2026-07-17: disclosed: CVE published to NVD