WSP MCP – WordPress MCP – Connect Claude, codex, antigravity or any other AI Agent <= 2.7.0 - Missing Authorization to Authenticated (Contributor+) Unauthorized Post and Media Modification
Strategic Overview
- Status
- Patched in 2.7.1
- Affected Version
<= 2.7.0- CVSS
- 4.3Medium
- Weakness type
- CWE-862 · Missing Authorization
- CVE
CVE-2026-93529
At a glance
CVE-2026-93529 is a medium-severity Missing Authorization vulnerability in the WSP MCP WordPress plugin, affecting versions <= 2.7.0. It carries a CVSS score of 4.3 (reachable over the network; low attack complexity). Exploitation requires an authenticated account at Contributor level or above. The issue is fixed in version 2.7.1; sites on affected versions should update now. Disclosed September 2026, reported by Ananda Dhakal.
Vulnerability Overview
The WSP MCP – WordPress MCP – Connect Claude, codex, antigravity or any other AI Agent plugin for WordPress is vulnerable to unauthorized access in all versions up to, and including, 2.7.0. This is due to missing object-level capability checks on caller-supplied post IDs in write ability callbacks, allowing Contributors to act on content they do not own or lack permission to modify. This makes it possible for authenticated attackers, with contributor-level access and above, to modify or delete posts, pages, and media items owned by higher-privileged users, including publishing content beyond their role's capabilities.
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.
CWE-862: Missing Authorization
Reaching this weakness in WSP MCP <= 2.7.0 takes an account at Contributor level or above. A missing authorization check means a function is reachable by anyone who can reach the endpoint, because the code never asks whether the caller is allowed to perform the action.
Any user who can reach the endpoint gets to run an action reserved for higher-privileged roles, from reading protected data to changing settings or content. For WSP MCP the fix is 2.7.1: builds <= 2.7.0 are affected, anything from 2.7.1 onward is not.
Remediation
Update to version 2.7.1, 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 2.7.1 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