CVE-2026-65566

AI Engine – MCP Server & AI Chatbot for WordPress, with Claude, ChatGPT & Gemini <= 3.8.8 - Cross-Site Request Forgery

2026-10-30 16:15
AndrewN

Strategic Overview

Status
Patched in 3.8.9
Affected Plugin
AI Engine – MCP Server & AI Chatbot for WordPress, with Claude, ChatGPT & Gemini
Affected Version
<= 3.8.8
CVSS
4.3Medium
Weakness type
CWE-352 · Cross-Site Request Forgery
CVE
CVE-2026-65566
View all AI Engine – MCP Server & AI Chatbot for WordPress, with Claude, ChatGPT & Gemini vulnerabilities

At a glance

CVE-2026-65566 is a medium-severity Cross-Site Request Forgery vulnerability in the AI Engine WordPress plugin, affecting versions <= 3.8.8. It carries a CVSS score of 4.3 (reachable over the network; low attack complexity). Exploitation requires no authentication. The issue is fixed in version 3.8.9; sites on affected versions should update now. Disclosed October 2026, reported by AndrewN.

Vulnerability Overview

The AI Engine – MCP Server & AI Chatbot for WordPress, with Claude, ChatGPT & Gemini plugin for WordPress is vulnerable to Cross-Site Request Forgery in all versions up to, and including, 3.8.8. This is due to missing or incorrect nonce validation on a function. This makes it possible for unauthenticated attackers to perform an unauthorized action via a forged request granted they can trick a site administrator into performing an action such as clicking on a link.

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.

CWE-352: Cross-Site Request Forgery

Reaching this weakness in AI Engine <= 3.8.8 takes a caller who can reach the endpoint. Cross-site request forgery abuses the fact that browsers attach a victim's cookies to any request, so a state-changing action that only checks who you are, not whether you meant to act, can be triggered from another site.

An attacker who gets a logged-in user to load a crafted page can perform that action as them, with the impact scaling to whatever the victim's role is allowed to do. For AI Engine the fix is 3.8.9: builds <= 3.8.8 are affected, anything from 3.8.9 onward is not.

Remediation

Update to version 3.8.9, or a newer patched version

How does WordSec protect against this?

The attempt arrives as an ordinary request to AI Engine: WordSec's web application firewall inspects request payloads before WordPress loads them. None of that substitutes for the fix: AI Engine 3.8.9 closes this, and updating the plugin is the step that ends it.

  • Firewall
  • Alerts

External References

https://www.cve.org/CVERecord?id=CVE-2026-65566https://www.wordfence.com/threat-intel/vulnerabilities/id/908c9c83-545d-40df-b7dc-4132359d675bhttps://nvd.nist.gov/vuln/detail/CVE-2026-65566

Related records

Vulnerability data © Defiant, Inc., provided under the Wordfence Intelligence T&C