CVE-2026-110732: AI Engine (WordPress plugin) · Missing Authorization
Affects AI Engine (WordPress plugin)Source CVE Database V5
Not known to be exploited · CVSS 7.5 High.
Data as of 30 Oct 2026, 07:14 UTC
Thin evidence
One scorer or none| CNA (Wordfence) | CVSS 3.1 | 7.5 |
|---|
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:HExploitation evidence
Disclosed: evidence found.
CVE published 30 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 29 Oct 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| tigroumeowAI Engine – MCP Server & AI Chatbot for WordPress, with Claude, ChatGPT & Gemini | Affected
| Fixed in– |
AI-suggested
Users should monitor the vendor's advisory for updates. Until a fix is available, administrators should be cautious when approving OAuth client registrations on the MCP consent screen and consider restricting access to the OAuth registration endpoint if possible. Implementing web application firewall (WAF) rules to block unauthorized access to the endpoint may help mitigate risk. Additionally, administrators should be aware of clickjacking risks and consider browser or plugin-based protections to prevent clickjacking attacks on the consent page.
Description
The AI Engine – MCP Server & AI Chatbot for WordPress plugin (versions up to 3.8.6) contains a missing authorization vulnerability in its MCP module's OAuth 2.1 Dynamic Client Registration endpoint. This endpoint allows unauthenticated users to register OAuth clients with attacker-controlled redirect URIs. If an administrator approves the attacker's client on the OAuth consent screen, the attacker can gain administrator-level access through the MCP tools. The consent page lacks protections against clickjacking, enabling attackers to trick administrators into approving malicious clients.
References
- wordfence.com/threat-intel/vulnerabilities/id/eb115a8a-35f8-426f-bb67-4a523f67cb34?source=cve (opens in a new tab)
- plugins.trac.wordpress.org/browser/ai-engine/tags/3.8.3/labs/mcp-oauth.php (opens in a new tab)
- plugins.trac.wordpress.org/browser/ai-engine/tags/3.8.3/labs/mcp-oauth.php (opens in a new tab)
- plugins.trac.wordpress.org/browser/ai-engine/tags/3.8.3/labs/mcp-oauth.php (opens in a new tab)
- plugins.trac.wordpress.org/browser/ai-engine/tags/3.8.3/labs/mcp-oauth.php (opens in a new tab)
- plugins.trac.wordpress.org/browser/ai-engine/tags/3.8.3/labs/mcp.php (opens in a new tab)
- plugins.trac.wordpress.org/changeset?reponame=&new=3760852%40ai-engine%2Ftags%2F3.8.7&old=3757660%40ai-engine%2Ftags%2F3.8.6 (opens in a new tab)
- plugins.trac.wordpress.org/changeset/3760851/ai-engine/trunk/labs/mcp-oauth.php (opens in a new tab)