CVE-2026-130121

7.2High

Published 18 Nov 2026 · NVD status: Deferred · AI triage by gemini-3.1-flash-lite

7.2CVSS

High

0CVSS v3.110

Attack vector
Network
Complexity
Low
Privileges
None
User action
None
Impact
Limited impact
Weakness
CWE-79

What an attacker gets

Unauthenticated attackers can execute arbitrary JavaScript in your WordPress site by triggering AI-generated comment replies. This requires the 'Comment Auto-Reply' automation to be set to 'Approve' for new replies.

Root cause

The insert_comment_reply_logic() function saves AI-generated content directly to the database using wp_insert_comment() without applying kses sanitization.

Affected versions

AI Puffer - MCP Server for Claude & ChatGPT (gpt3-ai-content-generator) versions up to and including 2.5.28.

CVSS v3.1 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N

Fix & remediation

Update to version 2.5.29 or later. Immediately change the 'Action on reply' setting in your Comment Auto-Reply automation tasks from 'Approve' to 'Hold for moderation'.

AI-suggested. Run it in staging first and check it against the vendor advisory. Why?

NVD description

The AI Puffer - MCP Server for Claude & ChatGPT, with AI Chatbot plugin for WordPress is vulnerable to Stored Cross-Site Scripting via AI-generated comment replies in all versions up to, and including, 2.5.28 due to insufficient sanitization of the AI model's output in the insert_comment_reply_logic() function, which saves replies with wp_insert_comment() and bypasses the kses filtering WordPress normally applies to comment content. This makes it possible for unauthenticated attackers to inject arbitrary web scripts in pages that will execute whenever a user accesses an injected page, by submitting a comment that leads the AI model to reproduce an HTML payload in its automated reply. This is only exploitable when an administrator has configured a Comment Auto-Reply automation task with 'Action on reply' set to 'Approve' (the default is 'Hold for moderation'), and the attacker's comment has been approved.

References

Source: nvd.nist.gov/vuln/detail/CVE-2026-130121