CVE-2026-53845: OpenClaw < 2026.5.6 - Skill-Command Dispatch Hook Bypass via Before-Tool-Call Hook Skipping

Published Jun 16, 2026
·
Updated

Summary

Skill-command dispatch could skip before-tool-call hooks. In affected versions, a skill command routed through the affected dispatch path could run without the same runBeforeToolCallHook coverage as other tool entry points.

This advisory is scoped to the named feature and configuration. It does not change OpenClaw's trusted-operator model: authenticated Gateway operators, installed plugins, and intentional local execution surfaces remain trusted unless a separate policy, approval, allowlist, sandbox, or auth boundary is crossed.

Impact

When the affected feature is enabled and reachable, this could miss hook-based auditing or policy parity for that command path. Practical impact depends on the operator's configuration and whether lower-trust input can reach that path.

Patched Versions

The first stable patched version is 2026.5.6.

Mitigations

avoid relying on hook-only enforcement for skill commands until patched. As general hardening, keep channel and tool allowlists narrow, avoid sharing one Gateway between mutually untrusted users, and disable the affected feature when it is not needed.

Other sources

OpenClaw before 2026.5.6 contains a hook bypass vulnerability where skill commands routed through the affected dispatch path skip before-tool-call hook coverage. Attackers can exploit this by sending skill commands through the vulnerable dispatch path to bypass hook-based auditing and policy enforcement mechanisms.

MITRE

Affected Software

4 affected componentsFixes available
OpenClaw OpenClaw<2026.5.6
OpenClaw Openclaw Node.js<2026.5.6
OpenClaw Openclaw Node.js=2026.5.6-beta1
npm/openclaw<=2026.5.5
2026.5.6

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade npm/openclaw to a version that resolves this vulnerability.

    Fixed in 2026.5.6
  2. Configuration

    Disable the affected skill-command dispatch path / feature in OpenClaw configuration when it is not required to prevent skill commands from bypassing runBeforeToolCallHook coverage.

    OpenClaw skill-command-dispatch-path (affected feature) = disabled
  3. Compensating control

    Keep channel and tool allowlists narrow (restrict to the minimum necessary), avoid sharing a single Gateway between mutually untrusted users, and ensure skill commands receive equivalent auditing/approval/sandboxing (do not rely on hook-only enforcement) until systems are upgraded to 2026.5.6.

Event History

Jun 16, 2026
CVE Published
via MITRE·06:04 PM
Data Sourced
via MITRE·06:04 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·07:17 PM
DescriptionSeverityWeaknessAffected Software
Jun 18, 2026
Advisory Published
via GitHub·08:16 PM
Data Sourced
via GitHub·08:16 PM
DescriptionSeverityWeaknessAffected Software
Free Weekly Intel

Don't miss critical vulnerabilities

Join thousands of security professionals who receive our weekly digest of trending CVEs, zero-days, and exploited vulnerabilities.

No spam. Unsubscribe anytime.

Frequently Asked Questions

1

What is the severity of CVE-2026-53845?

The severity of CVE-2026-53845 is rated as low with a score of 2.3.

2

How do I fix CVE-2026-53845?

To fix CVE-2026-53845, update to OpenClaw version 2026.5.6 or later.

3

What systems are affected by CVE-2026-53845?

CVE-2026-53845 affects OpenClaw versions prior to 2026.5.6.

4

What type of vulnerability is CVE-2026-53845?

CVE-2026-53845 is a skill-command dispatch hook bypass vulnerability.

5

What are the potential impacts of CVE-2026-53845?

The potential impact of CVE-2026-53845 is that skill commands may bypass important execution hooks.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203