OpenClaw hook ingress can start automated agent runs using a configured hook token. In affected releases, a hook-triggered run could select a bundled CLI backend that received owner-scoped MCP loopback authority instead of a scope appropriate for hook ingress.
This issue affects the boundary between hook-token automation and owner-only MCP tools. It does not affect deployments with hooks disabled.
This affects deployments where hooks are enabled, /hooks/agent is reachable with a valid hook token, and a bundled CLI backend can be selected for the hook-triggered run.
A caller with the hook token could cause the spawned CLI runtime to see or call MCP tools that should have been owner-only. The practical impact depends on which MCP tools are available; the reported proof used persistent cron state as a representative owner-only action.
The first stable patched version is 2026.5.20.
Fixed in the 2026.5.20 stable release.
Upgrade to openclaw@2026.5.20 or later. Keep hook tokens secret, restrict network access to hook endpoints, and disable hooks when they are not needed.
{
"cwe_ids": [
"CWE-200",
"CWE-266",
"CWE-284"
],
"github_reviewed": true,
"github_reviewed_at": "2026-07-02T16:05:03Z",
"nvd_published_at": "2026-06-11T21:16:23Z",
"severity": "HIGH"
}