CVE-2026-79745
Received Received - Intake

Privilege Escalation in MCPHub via Unauthorized Prompt/Resource Tampering

Publication date: 2026-08-31

Last updated on: 2026-08-31

Assigner: GitHub, Inc.

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.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-08-31
Last Modified
2026-08-31
Generated
2026-08-31
AI Q&A
2026-08-31
EPSS Evaluated
N/A
NVD
CVE-2026-79745
EUVD
EUVD-2026-68689

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
mcphub mcphub to 1.0.32 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-862 The product does not perform an authorization check when an actor attempts to access a resource or perform an action.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability in MCPHub (CVE-2026-79745) allows non-admin users to create, overwrite, or shadow global prompt templates and resources. The affected POST/PUT routes for /api/prompts* and /api/resources* lack admin checks, letting attackers modify globally-served records that all users access. This enables stored prompt injection attacks where malicious templates are served to other users' LLM sessions.

Detection Guidance

Check MCPHub version with: npm list mcphub. If version is 1.0.31 or earlier, the system is vulnerable. Inspect logs for unauthorized POST/PUT requests to /api/prompts* or /api/resources* from non-admin users. Review global prompt/resource templates for unexpected modifications.

Impact Analysis

An attacker with basic authenticated access could inject malicious prompts or resources that override legitimate ones. This could lead to stored prompt injection attacks, where other users' LLM sessions receive tampered templates, potentially causing data leaks, unauthorized actions, or system compromise. The integrity of shared system resources is violated.

Compliance Impact

This vulnerability could violate compliance requirements that mandate strict access controls and data integrity protections. Unauthorized modifications to global prompts/resources may lead to unauthorized data exposure or processing, conflicting with GDPR's integrity and confidentiality principles and HIPAA's safeguards for protected health information.

Mitigation Strategies

Upgrade MCPHub to version 1.0.32 or later immediately. Verify admin checks are enforced on /api/prompts* and /api/resources* routes. Audit all global prompts/resources for tampering and remove unauthorized entries.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-79745. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart