What is the CVSS score of CVE-2026-8719?

CVE-2026-8719 has a CVSS 3.1 base score of 8.8 (High). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.0%.

Which versions of AI Engine are affected by CVE-2026-8719?

CVE-2026-8719 is a privilege escalation vulnerability in AI Engine WordPress plugin v3.4.9 affecting authenticated users who can escalate to administrator privileges through improper OAuth token…

How to fix or mitigate CVE-2026-8719?

Within 24 hours: Audit WordPress sites running AI Engine v3.4.9 for active users and recent MCP OAuth token activity; disable the plugin if not critical to operations. Within 7 days: Contact AI Engine developers for patched version status and timeline; implement IP whitelisting or WAF rules to restrict MCP endpoints if the plugin cannot be removed. Within 30 days: Upgrade to patched version when available; conduct access logs review for evidence of privilege escalation attempts.

AI Engine CVE-2026-8719

EUVD-2026-30678 HIGH

Improper Privilege Management (CWE-269)

2026-05-17 Wordfence

GHSA-39f2-3f7m-6r66

WordPress Privilege Escalation Wordpress Plugin Ai Engine The Chatbot Ai Framework Mcp For Wordpress Tigroumeow

8.8

CVSS 3.1 · NVD

Severity by source

NVD PRIMARY

8.8 HIGH

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

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

May 17, 2026 - 03:42 vuln.today

DescriptionCVE.org

The AI Engine - The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Privilege Escalation in version 3.4.9. This is due to missing WordPress capability enforcement in the MCP OAuth bearer-token authorization path, where any valid OAuth token causes MCP access to be granted without verifying administrator privileges. This makes it possible for authenticated (Subscriber+) attackers to invoke admin-level MCP tools and escalate privileges to Administrator.

AnalysisAI

Authenticated attackers can escalate privileges to Administrator in AI Engine WordPress plugin version 3.4.9 through improper authorization in the MCP OAuth bearer-token implementation. The plugin accepts any valid OAuth token for Model Context Protocol (MCP) access without verifying administrator privileges, allowing low-privileged users (Subscriber+) to execute admin-level MCP tools. No public exploit or active exploitation identified at time of analysis.

Technical ContextAI

AI Engine is a WordPress plugin providing chatbot and AI framework functionality with Model Context Protocol (MCP) support. The vulnerability stems from CWE-269 (Improper Privilege Management) where the OAuth bearer-token authorization path for MCP access fails to enforce WordPress capability checks. When processing OAuth tokens, the plugin grants MCP access based solely on token validity rather than verifying the token holder has administrator privileges, effectively bypassing WordPress's role-based access control system.

RemediationAI

Update to a version after 3.4.9 that includes the security fix implemented in changeset 3533527 (https://plugins.trac.wordpress.org/changeset/3533527/ai-engine). The changeset indicates a patch has been committed upstream. As an immediate workaround, disable the MCP functionality if not required, or restrict user registration to prevent untrusted users from obtaining Subscriber accounts. Monitor user accounts for unexpected privilege changes and review administrator account creation logs.