Which versions of OpenClaw are affected by CVE-2026-62186?

OpenClaw versions before 2026.6.8 contain a privilege escalation vulnerability that permits authenticated users with lower privilege levels to perform unrestricted administrative operations by…

How to fix or mitigate CVE-2026-62186?

Within 24 hours: identify and inventory all systems running OpenClaw versions before 2026.6.8. Within 7 days: implement network-layer or application-layer restrictions on HTTP model-override input paths and deploy enhanced monitoring to detect admin-level operations from lower-privileged user accounts. Within 30 days: monitor vendor advisories for patch availability (targeting version 2026.6.8 or later) and develop a patch deployment timeline; apply the vendor patch to all affected systems immediately upon release.

OpenClaw CVE-2026-62186

Q: What is the CVSS score of CVE-2026-62186?

CVE-2026-62186 has a CVSS 4.0 base score of 7.2 (High). CVSS vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:L/VA:L/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: 0.2%.

HIGH

Missing Authorization (CWE-862)

2026-07-13 VulnCheck

Authentication Bypass Openclaw

7.2

CVSS 4.0 · Vendor: VulnCheck

Severity by source

Vendor (VulnCheck) PRIMARY

7.2 HIGH

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:L/VA:L/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

7.6 HIGH

Network-reachable, low-complexity call needs an authenticated low-trust account (PR:L), and bypassing authorization exposes restricted operations and data (C:H) with limited integrity and availability effect.

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

4.0 AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:L/VA:L/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

None

Scope

Lifecycle Timeline

Analysis Generated

Jul 13, 2026 - 22:02 vuln.today

CVE Published

Jul 13, 2026 - 21:30 cve.org

HIGH 7.2

DescriptionCVE.org

OpenClaw versions before 2026.6.8 contain an authorization bypass vulnerability in OpenAI-compatible HTTP model overrides that allows lower-trust callers to perform actions requiring stronger authorization checks. Attackers can exploit misconfigured input paths to bypass admin authorization policies and execute restricted operations.

AnalysisAI

Privilege escalation in OpenClaw before 2026.6.8 lets a lower-trust, already-authenticated caller invoke admin-restricted operations by abusing OpenAI-compatible HTTP model-override input paths, bypassing the authorization checks that should gate those actions. The flaw was reported by VulnCheck and stems from missing authorization (CWE-862) on override-driven request handling. There is no public exploit identified at time of analysis and the CVE is not listed in CISA KEV.

Technical ContextAI

OpenClaw exposes an OpenAI-compatible HTTP API in which callers can supply 'model override' parameters to steer which model or backend handles a request. Because the affected versions perform incomplete authorization on these override input paths (CWE-862, Missing Authorization), the code reaches privileged operation handlers without re-validating that the caller holds the required admin trust level. The single affected component per the CPE is cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:*:*:*, i.e. the OpenClaw application itself across all versions prior to the fix. The root cause is an authorization gap where trust is inherited from a lower-privileged context rather than enforced per privileged action.

RemediationAI

Vendor-released patch: upgrade to OpenClaw 2026.6.8 or later, which restores the authorization checks on the OpenAI-compatible HTTP model-override paths; see the GitHub Security Advisory GHSA-jhfx-v2j8-x3m6 (https://github.com/openclaw/openclaw/security/advisories/GHSA-jhfx-v2j8-x3m6) and the VulnCheck advisory (https://www.vulncheck.com/advisories/openclaw-authorization-bypass-via-http-model-override). If you cannot upgrade immediately, reduce exposure by restricting who can reach the model-override and API endpoints - place the OpenClaw HTTP interface behind an authenticating reverse proxy or network ACL limited to trusted admin identities, and strip or block the model-override input parameters at the gateway if your deployment does not require them (trade-off: clients that legitimately switch models will break). Also tighten account provisioning so low-trust accounts cannot authenticate to the API at all, since the flaw requires only a low-privilege authenticated caller; these are stopgaps and do not replace the 2026.6.8 upgrade.