OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization
Summary
| CVE | CVE-2026-54140 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-11-05 17:18:18 UTC |
| Updated | 2026-11-06 21:41:14 UTC |
| Description | OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13. |
Risk And Classification
Primary CVSS: v3.1 8.3 HIGH from [email protected]
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H
EPSS: 0.005540000 probability, percentile 0.464190000 (date 2026-11-06)
Problem Types: CWE-1427 CWE-1427:
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 3.1 | [email protected] | Secondary | 8.3 | HIGH | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H |
| 3.1 | CNA | DECLARED | 8.3 | HIGH | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H |
CVSS v3.1 Breakdown
Attack Vector
NetworkAttack Complexity
HighPrivileges Required
NoneUser Interaction
RequiredScope
ChangedConfidentiality
HighIntegrity
HighAvailability
HighCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | Tinyhumansai | Openhuman | affected < 0.57.13 | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/tinyhumansai/openhuman/pull/3215 | [email protected] | github.com | |
| github.com/tinyhumansai/openhuman/releases/tag/v0.57.13 | [email protected] | github.com | |
| github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f7... | [email protected] | github.com | |
| github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752 | [email protected] | github.com | |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.