CVE-2026-54140 (CVSS 8.3)

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.

Is your site exposed to CVE-2026-54140?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

8.3

HIGH

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H

EPSS — Exploit Prediction

0.0055

Probability of exploitation

0.47%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

References

Other References

https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e https://github.com/tinyhumansai/openhuman/pull/3215 https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13 https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752 https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752

Frequently Asked Questions

What is CVE-2026-54140? +

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. It has a CVSS v3.1 base score of 8.3 (HIGH).

How severe is CVE-2026-54140? +

CVE-2026-54140 has a CVSS v3.1 score of 8.3 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0055, placing it in the 0th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-54140? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

CVE-2026-54140