WordPress MCP Connector Authorization Bypass Grants Admin Access

The MountDev AI MCP Connector for WordPress plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 1.6.1. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated attackers to obtain an administrator-bound OAuth Bearer token via a self-registered client, granting full administrator-equivalent access to the plugin's MCP tool surface and all exposed WordPress content, users, and options. This is exploitable by combining the publicly accessible Dynamic Client Registration endpoint, which allows unauthenticated callers to register arbitrary OAuth clients with an attacker-controlled redirect_uri, with the unprotected authorization endpoint to complete the full OAuth flow without any administrator interaction.

Casky was already ahead

This CVE exploits attack patterns that Casky's 283matched skills already investigate — long before this vulnerability was disclosed. Claude's reasoning model maps these techniques to MITRE ATT&CK, so practitioners who ran these skills have already seen the threat behaviour in their findings.

Analysis

The MountDev AI MCP Connector for WordPress plugin contains a critical authorization bypass vulnerability (CVE-2026-15015, CVSS 9.8) that allows unauthenticated attackers to obtain administrator-level OAuth Bearer tokens. By exploiting improper authorization verification, attackers can self-register clients and bypass authentication controls entirely, gaining full administrative access to the plugin's Model Context Protocol (MCP) tool surface and all exposed WordPress content, user data, and system configuration. This vulnerability affects all versions up to 1.6.1 and poses an immediate risk to any WordPress installation using this plugin, as it transforms an unauthenticated user into an administrator-equivalent threat actor with unrestricted access to sensitive operations and data.

Casky's skill mapping correlates this vulnerability to MITRE ATT&CK techniques TA0004 (Privilege Escalation) and TA0006 (Credential Access), with 283 matching security skills powered by Claude's extended reasoning. Practitioners using Casky would identify attack patterns including: (1) detection of OAuth token generation from unauthenticated requests to the MCP Connector's authorization endpoint, flagging anomalous token issuance without prior authentication; (2) behavioral analysis of client self-registration workflows that bypass standard authorization checks; (3) monitoring for privilege escalation indicators where low-privilege or anonymous sessions suddenly obtain administrator-bound credentials; and (4) credential access detection focusing on OAuth Bearer token acquisition through unauthorized channels. These skills enable practitioners to spot the characteristic signatures of this vulnerability—unusual administrative token generation, missing authorization validation logs, and suspicious self-registered client activities—before attackers can leverage them for data exfiltration or system compromise.

Live Threat IntelligenceComing soon

Casky Risk Score

—

EPSS Probability

—

Shodan Exposure

—

GreyNoise Signal

—

Composite risk scoring from EPSS, CISA KEV, Shodan, and GreyNoise — 21 security APIs correlated into a single Casky Risk Score. Coming in Casky Pro. Join early access →

283 Casky skills cover this attack pattern

These skills use Claude AI's reasoning model to surface findings in the same attack categories as CVE-2026-15015.

abusing-dpapi-for-credential-access

red teaming · high

Run

abusing-shadow-credentials-for-privesc

red teaming · high

Run

Access with Stolen Session Cookie

identity access management · low

Run

MITRE ATT&CK Techniques

TA0004 TA0006

Investigate the attack patterns behind CVE-2026-15015

Casky has 283 skills that investigate the attack patterns behind CVE-2026-15015. Run one and get CVSS-scored findings in 3 minutes.

Run the skill that detects this →

X Instagram LinkedIn