Which versions of OpenClaw are affected by CVE-2026-53829?

OpenClaw versions prior to 2026.5.18 contain a command approval bypass flaw that allows authenticated users to execute malicious instructions hidden from reviewing administrators.. A patch is available.

How to fix or mitigate CVE-2026-53829?

24 hours: Inventory all OpenClaw installations, document current versions, and identify systems processing sensitive commands through approval workflows. 7 days: Implement compensating controls-restrict approval authority to senior staff only, add secondary approval for commands exceeding defined length thresholds, and enable detailed logging of submitted vs. executed commands. 30 days: Monitor vendor advisories for OpenClaw version 2026.5.18 or later; upgrade immediately upon availability; conduct forensic review of approval logs from past 90 days for anomalies.

OpenClaw CVE-2026-53829

Q: What is the CVSS score of CVE-2026-53829?

CVE-2026-53829 has a CVSS 4.0 base score of 8.5 (High). CVSS vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. EPSS exploitation probability: 0.0%.

EUVD-2026-36617 HIGH

User Interface (UI) Misrepresentation of Critical Information (CWE-451)

2026-06-12 VulnCheck

GHSA-92qj-8g54-qmph

Authentication Bypass Openclaw

8.5

CVSS 4.0 · Vendor: VulnCheck

Severity by source

Vendor (VulnCheck) PRIMARY

8.5 HIGH

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

vuln.today AI

8.0 HIGH

Network-reachable approval workflow with a low-privileged authenticated submitter (PR:L) and a required approver click (UI:R); successful execution yields full C/I/A impact via the exec runner.

3.1 AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H

4.0 AV:N/AC:L/AT:N/PR:L/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (VulnCheck).

CVSS VectorVendor: VulnCheck

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

Scope

Lifecycle Timeline

Patch available

Jun 13, 2026 - 02:00 EUVD

Analysis Generated

Jun 12, 2026 - 22:33 vuln.today

DescriptionCVE.org

OpenClaw before 2026.5.18 contains an approval display truncation vulnerability allowing authenticated users to hide command suffixes from approvers. Attackers can submit oversized exec commands with benign prefixes and malicious suffixes to execute unauthorized operations after approval.

AnalysisAI

Command approval bypass in OpenClaw versions prior to 2026.5.18 allows authenticated users to smuggle malicious instructions past human approvers by exploiting how the approval UI truncates oversized exec commands. The flaw (CWE-451, UI misrepresentation) lets an attacker craft a request with a benign-looking prefix while a malicious suffix is hidden from the reviewer's display, resulting in unauthorized execution once the request is approved. No public exploit identified at time of analysis and the CVE is not currently listed in CISA KEV.

Technical ContextAI

OpenClaw appears to be an agent/automation framework that gates exec command execution behind a human approval workflow. The root cause is CWE-451 (UI Misrepresentation of Critical Information): the approval surface renders commands in a way that visually truncates long inputs, so the bytes the approver sees are not the bytes that get executed. Because validation/display and execution operate on different views of the same string, an attacker can craft a payload whose visible prefix is innocuous (e.g. a routine read) while the hidden suffix performs arbitrary operations once approved. The affected CPE is cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:*:*:*, covering all versions up to the fixed 2026.5.18 release.

RemediationAI

Vendor-released patch: upgrade OpenClaw to 2026.5.18 or later, which corrects the approval-display truncation; see the GHSA at https://github.com/openclaw/openclaw/security/advisories/GHSA-xww8-gqvh-92x9 and the VulnCheck advisory at https://www.vulncheck.com/advisories/openclaw-command-truncation-in-exec-approval-display. Until the upgrade is rolled out, compensating controls include enforcing a strict maximum length on exec command submissions at the request layer (rejecting any command longer than what the approval UI can fully render, with the trade-off of breaking legitimate long commands), requiring approvers to view the raw command via a CLI or log diff rather than the truncated UI before clicking approve (slower approvals, but eliminates the display gap), and tightening the role of low-privileged submitters by restricting who can issue exec requests at all (reduces functionality for routine users). Audit recent approved exec actions for suspicious suffixes hidden past the typical UI cutoff.