The QQBot streaming command in OpenClaw versions prior to 2026.4.29 can mutate configuration without an explicit non-wildcard allowFrom entry. This means a QQBot sender reaching the affected command could change configuration settings outside intended administrative policies. The vulnerability is scoped to this feature and does not alter the trusted-operator model of OpenClaw. The practical impact depends on operator configuration and exposure of the command to lower-trust inputs.

If the affected feature is enabled and accessible, unauthorized mutation of QQBot streaming configuration can occur, potentially bypassing intended administrative controls. This could lead to configuration changes outside the intended policy, affecting system behavior or security posture. The impact depends on how the operator configures access and whether untrusted inputs can reach the vulnerable command path.

A fix is available in OpenClaw version 2026.4.29. Until upgrading, it is recommended to disable the QQBot streaming command or restrict its use to explicitly trusted QQBot senders. Additionally, operators should maintain narrow channel and tool allowlists, avoid sharing Gateways between mutually untrusted users, and disable the affected feature when not needed.