CVE-2026-109382
Received Received - Intake

Sensitive Information Disclosure in WSP MCP AI Agents Connector

Publication date: 2026-10-16

Last updated on: 2026-10-16

Assigner: Wordfence

Description
The WSP MCP AI Agents Connector plugin for WordPress is vulnerable to Sensitive Information Disclosure in versions up to, and including, 2.9.5. This is due to the wsp_get_posts MCP tool being registered with an empty capability requirement while the MCP endpoint's authenticate() method accepts any logged-in user, and the wsp_execute_get_posts() callback honouring a caller-supplied status=all argument that expands into a WP_Query over 'publish', 'draft', 'pending' and 'future' posts with no author or ownership filter. This makes it possible for authenticated attackers, with Subscriber-level access and above, to read the titles, URLs, authors, categories, tags and 40-word excerpts of every unpublished (draft/pending/scheduled) post on the site.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-10-16
Last Modified
2026-10-16
Generated
2026-10-16
AI Q&A
2026-10-16
EPSS Evaluated
N/A
NVD
CVE-2026-109382
EUVD
EUVD-2026-102794

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
bilalnaseer WSP MCP – Free MCP Plugin for WordPress: Connect Claude, ChatGPT & AI Agents 0

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-863 The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

The WSP MCP AI Agents Connector plugin for WordPress has a flaw where sensitive unpublished post data can be accessed by authenticated users with Subscriber-level access or higher. The plugin improperly exposes post titles, URLs, authors, categories, tags, and excerpts of draft, pending, or scheduled posts due to weak access controls in the MCP tool registration and query handling.

Detection Guidance

Check WordPress sites using the WSP MCP AI Agents Connector plugin version 2.9.5 or lower. Look for unauthorized access to unpublished posts via the wsp_get_posts MCP tool. Review server logs for suspicious queries targeting post status parameters.

Impact Analysis

Attackers with basic user access could steal unpublished content, including sensitive drafts or future posts, potentially exposing confidential information before it is ready for publication. This could lead to data leaks, reputational damage, or unauthorized access to proprietary or private content.

Compliance Impact

This vulnerability could violate GDPR by exposing personal data in unpublished posts or HIPAA by leaking sensitive health information in drafts. Unauthorized access to unpublished content may result in non-compliance with data protection requirements, leading to legal penalties or loss of certification.

Mitigation Strategies

Update the WSP MCP AI Agents Connector plugin to the latest version. Remove or restrict Subscriber-level access if not required. Implement additional authentication checks for MCP endpoints. Monitor for unauthorized post access attempts.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-109382. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart