CVE-2026-54140
OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization
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.
INFO
Published Date :
Nov. 5, 2026, 5:18 p.m.
Last Modified :
Nov. 5, 2026, 5:18 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
Affected Products
The following products are affected by CVE-2026-54140
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Update OpenHuman to version 0.57.13 or later.
- Ensure MCP server configurations are trusted.
- Neutralize instructions from external sources.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-54140.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-54140 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-54140
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-54140 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-54140 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Nov. 05, 2026
Action Type Old Value New Value Added 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. Added CVSS V3.1 AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/54xxx/CVE-2026-54140.json">CVE-2026-54140</a> Added Reference https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e Added Reference https://github.com/tinyhumansai/openhuman/pull/3215 Added Reference https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13 Added Reference https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752