HighVulnerabilityLLM-specific

CVE-2026-79745: MCPHub endpoints let non-admin users overwrite global records

Source: NVD(opens in a new tab)
Identifier: CVE-2026-79745
Published: August 31, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

MCPHub, a hub for managing and orchestrating multiple MCP servers and APIs, performs no role checking on its built-in prompt and resource controllers before version 1.0.32. Any authenticated non-admin user can call the mutating POST/PUT /api/prompts* and POST/PUT /api/resources* routes, creating, overwriting or shadowing global prompt templates and resources that are served to all users. Because these records are consulted before any connected MCP server, the tampering can also lead to prompt injection in other users' LLM sessions.

Mitigation

Fixed in 1.0.32.

Details

Scores and exploitation

CVSS score: 7.1(high)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:L
Attack vector: network
Attack complexity: low
Privileges required: low
User interaction: none
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 5, 2026.
Disclosure date: August 31, 2026

Weaknesses and techniques

Weakness (CWE): CWE-862
Attack pattern (CAPEC): CAPEC-122
AI threat technique (MITRE ATLAS): AML.T0051

Classification

Attack type: Prompt injection
Attack sophistication: Trivial
AI component targeted: Plugin
Impact: Integrity,
Safety
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-79745

First tracked: August 31, 2026 at 08:08 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Topics

Model Context Protocol

Summary

Mitigation

Topics

Related items