Description
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.
Published: 2026-08-31
Score: 7.1 High
EPSS: n/a
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Impact

MCPHub implements a missing authorization check on its built-in prompt and resource endpoints. The POST/PUT /api/prompts* and /api/resources* routes are attached to an authenticated router with no admin gate and the handlers never read the user identity. This flaw allows any authenticated user to create, overwrite, and shadow global prompt templates and resources that are subsequently served to all users. The resulting integrity violation can lead to stored prompt injection in downstream language-model sessions.

Affected Systems

The vulnerability exists in the MCPHub product from the vendor samanhappy. All versions prior to 1.0.32 are affected.

Risk and Exploitability

The CVSS score of 7.1 indicates a medium‑severity integrity issue. The flaw can be exploited remotely by any authenticated user via normal API calls to /api/prompts* or /api/resources*. The EPSS score is not yet available, and the vulnerability is not listed in the CISA KEV catalog. Nonetheless, any user with access can tamper with global templates, potentially allowing malicious prompt injection, making it a moderate to high risk for environments that rely on MCPHub for LLM orchestration.

Generated by OpenCVE AI on August 31, 2026 at 20:06 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Upgrade to MCPHub v1.0.32 or later to apply the missing authorization fix.
  • If an upgrade is not immediately possible, restrict the /api/prompts* and /api/resources* endpoints to administrative users only by reconfiguring the API gateway or firewall rules.
  • Remove or rebuild any tampered global prompt templates or resources that may have been created by non‑admin users to eliminate potential malicious content.

Generated by OpenCVE AI on August 31, 2026 at 20:06 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Mon, 31 Aug 2026 18:00:00 +0000

Type Values Removed Values Added
Description MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in prompt and resource controllers perform no role checking. The mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes are attached to the authenticated router with no admin gate, and the handlers never read req.user. The DAO singletons they write are consulted first — ahead of any connected MCP server — for every session in handleGetPromptRequest / handleReadResourceRequest. A non-admin can therefore create, overwrite, and shadow global prompt templates and resources that all other users are served. The scored impact is the unauthorized integrity violation (creation/tampering/shadowing of globally-served records); stored prompt injection into other users' LLM sessions is a downstream consequence of that tampering. This issue has been patched in version 1.0.32.
Title MCPHub: Missing Authorization on Built-in Prompt & Resource CRUD (Unauthorized Tampering of Globally-Served Templates/Resources)
Weaknesses CWE-862
References
Metrics cvssV3_1

{'score': 7.1, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L'}

Subscriptions

No data.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-08-31T17:56:17.622Z

Reserved: 2026-08-25T14:08:18.108Z

Link: CVE-2026-79745

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-08-31T18:17:19.910

Modified: 2026-08-31T18:17:19.910

Link: CVE-2026-79745

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-31T20:15:05Z

Weaknesses