WSP MCP <= 2.9.5 - Authenticated (Subscriber+) Sensitive Information Disclosure via Broken Access Control to 'wsp_get_posts' MCP Tool
Strategic Overview
- Status
- Patched in 2.9.6
- Affected Version
<= 2.9.5- CVSS
- 6.5Medium
- Weakness type
- CWE-863 · Incorrect Authorization
- CVE
CVE-2026-109382
At a glance
CVE-2026-109382 is a medium-severity Incorrect Authorization vulnerability in the WSP MCP WordPress plugin, affecting versions <= 2.9.5. It carries a CVSS score of 6.5 (reachable over the network; low attack complexity; high confidentiality impact). Exploitation requires an authenticated account at Subscriber level or above. The issue is fixed in version 2.9.6; sites on affected versions should update now. Disclosed October 2026, reported by Wordfence PRISM.
Vulnerability Overview
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Subscriber-level access and above, to read the titles, URLs, authors, categories, tags and 40-word excerpts of every unpublished (draft/pending/scheduled) post on the site.
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 interaction from a victim user. A successful exploit has high impact on confidentiality.
CWE-863: Incorrect Authorization
WSP MCP <= 2.9.5 carries this weakness at publish, and reaching it takes an account at Subscriber level or above. Incorrect authorization means a permission check exists but evaluates the wrong thing, so it passes for callers it was meant to stop.
The action runs for users the code intended to exclude, with the same effect as having no check at all. For WSP MCP the fix is 2.9.6: builds <= 2.9.5 are affected, anything from 2.9.6 onward is not.
Remediation
Update to version 2.9.6, or a newer patched version
How does WordSec protect against this?
Because it turns on account access, WordSec's login security is the relevant layer: role-based two-factor, captcha and brute-force limits raise the cost of getting the account this needs. None of that substitutes for the fix: WSP MCP 2.9.6 closes this, and updating the plugin is the step that ends it.
- Login Security
- Alerts
External References
Related records
Other vulnerabilities in WSP MCP – Free MCP Plugin for WordPress: Connect Claude, ChatGPT & AI Agents
Vulnerability data © Defiant, Inc., provided under the Wordfence Intelligence T&C