GitHub Advisoryadvisory · npm
GHSA-6fvr-66p3-3qj4 OpenClaw: Hook-triggered CLI runs could receive owner MCP tool authority
HIGH
Official page ↗
- Aliases
- CVE-2026-53814
- Ecosystem
- npm
- Packages
- openclaw
- Severity
- High
- CVSS vector
- CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:L
- Weaknesses
- CWE-200, CWE-266, CWE-284
- Reviewed
- 2026-07-02
Affected packages
• npm openclaw: < 2026.5.20 → fixed in 2026.5.20
Description
Summary
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.
Affected configurations
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.
Impact
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.
Patched Versions
The first stable patched version is `2026.5.20`.
Fixed in the `2026.5.20` stable release.
Mitigations
Upgrade to `[email protected]` or later. Keep hook tokens secret, restrict network access to hook endpoints, and disable hooks when they are not needed.
Related
Alias · CVE (1)
- CVE-2026-53814 OpenClaw before 2026.5.20 contains a privilege escalation vulnerability where hook-triggered agent runs incorrectly receive owner-scoped… vulnerability