Skip to main content
CVE-2026-130121VulnerabilityPublished

The AI Puffer - MCP Server for Claude & ChatGPT, with AI Chatbot plugin for WordPress is vulnerable to Stored

Source GCVE Database

0
Compare
Authoritative record:CVE-2026-130121· High 7.2

Not known to be exploited · CVSS 7.2 High.

Data as of 18 Nov 2026, 08:06 UTC

CVSS 3.1 base score
7.2High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (Wordfence)CVSS 3.17.2
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 18 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq 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 17 Nov 2026.

What to do

Affected software

ProductAffectedFixed in
senolsAI Puffer – MCP Server for Claude & ChatGPT, with AI ChatbotAffected
  • <=2.5.28
Fixed in–

AI-suggested

Administrators should verify and adjust the Comment Auto-Reply automation settings to ensure that the 'Action on reply' is not set to 'Approve' automatically, reverting to the default 'Hold for moderation' to prevent automatic publication of potentially malicious AI-generated replies. Monitor vendor advisories for any forthcoming patches or updates addressing this issue.

Description

The AI Puffer - MCP Server for Claude & ChatGPT, including its AI Chatbot plugin for WordPress, is vulnerable to a stored cross-site scripting (XSS) flaw in all versions up to and including 2.5.28. This vulnerability arises from insufficient sanitization of AI-generated comment replies, allowing unauthenticated attackers to inject malicious scripts that execute when users view the affected pages. Exploitation requires that an administrator has configured the Comment Auto-Reply automation task with the 'Action on reply' set to 'Approve' and that the attacker's comment is approved.

References

Community reviews

Loading reviews…