CVE-2026-81805

SiteSkite MCP AI – Connector for Claude, ChatGPT, Cursor & WordPress WebOps <= 2.1.5 - Unauthenticated Privilege Escalation

2026-09-09 00:00

Strategic Overview

Status: Patched in 2.1.6
Affected Plugin: SiteSkite MCP AI – Connector for Claude, ChatGPT, Cursor & WordPress WebOps
Affected Version: <= 2.1.5
CVSS: 7.3High
Weakness type: CWE-269 · Improper Privilege Management
CVE: CVE-2026-81805

View all SiteSkite MCP AI – Connector for Claude, ChatGPT, Cursor & WordPress WebOps vulnerabilities

At a glance

CVE-2026-81805 is a high-severity Improper Privilege Management vulnerability in the SiteSkite MCP AI WordPress plugin, affecting versions <= 2.1.5. It carries a CVSS score of 7.3 (reachable over the network; low attack complexity). Exploitation requires no authentication. The issue is fixed in version 2.1.6; sites on affected versions should update now. Disclosed September 2026, reported by Ananda Dhakal.

Vulnerability Overview

The SiteSkite MCP AI – Connector for Claude, ChatGPT, Cursor & WordPress WebOps plugin for WordPress is vulnerable to Privilege Escalation in all versions up to, and including, 2.1.5. This is due to insufficient restriction on the capabilities a user may grant themselves. This makes it possible for unauthenticated attackers to elevate their privileges beyond those intended for their role.

Technical Analysis

The vector marks this flaw as remotely reachable over the network, with low attack complexity — no special timing or configuration is needed, and no privileges on the target site, and no interaction from a victim user.

CWE-269: Improper Privilege Management

Reaching this weakness in SiteSkite MCP AI <= 2.1.5 takes no account at all. Improper privilege management means the code lets an account end up with capabilities its role should not have.

It converts a low-privileged account into an administrative one, which makes every other restriction on the site irrelevant. For SiteSkite MCP AI the fix is 2.1.6: builds <= 2.1.5 are affected, anything from 2.1.6 onward is not.

Remediation

Update to version 2.1.6, or a newer patched version

How does WordSec protect against this?

This one needs no account at all, which puts it outside what login hardening can reach; WordSec's login security narrows the account-level paths around it, and the firewall is what inspects the request itself. None of that substitutes for the fix: SiteSkite MCP AI 2.1.6 closes this, and updating the plugin is the step that ends it.

Login Security
Alerts

External References

https://www.cve.org/CVERecord?id=CVE-2026-81805 https://www.wordfence.com/threat-intel/vulnerabilities/id/60e8b120-b9ba-4f56-b47b-b06cf188febc https://nvd.nist.gov/vuln/detail/CVE-2026-81805

CVSS Vector

7.3

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

Base

Attack VectorNetwork
Attack ComplexityLow
Privileges RequiredNone
User InteractionNone
ScopeUnchanged
ConfidentialityLow
IntegrityLow
AvailabilityLow

This record contains material that is subject to copyright

CVE Usage: MITRE hereby grants you a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, sublicense, and distribute Common Vulnerabilities and Exposures (CVE®). Any copy you make for such purposes is authorized provided that you reproduce MITRE's copyright designation and this license in any such copy.

https://www.cve.org/Legal/TermsOfUse

Defiant hereby grants you a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, sublicense, and distribute this software vulnerability information. Any copy of the software vulnerability information you make for such purposes is authorized provided that you include a hyperlink to this vulnerability record and reproduce Defiant's copyright designation and this license in any such copy.

https://www.wordfence.com/wordfence-intelligence-terms-and-conditions/