Skip to content
Fencer Intel
high 8.3

CVE-2026-54140 json

OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization

published last mo. modified 2d ago also EUVD-2026-117577 , GHSA-g6j9-89xv-v752

Unreviewed: the maintainers' own advisory

Published by the maintainers on their GitHub repository tinyhumansai/openhuman. GitHub has not reviewed it into the GitHub Advisory Database, so the affected packages and versions are the maintainers' word. Read the full advisory on GitHub.

cvss
8.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.6%
EPSS 0.6% chance of exploitation in 30 days, percentile 46%
public exploits
0
none known

Summary

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.

Patch / fix

Is CVE-2026-54140 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
2d ago

Exploit prediction

0.55% chance of exploitation in the next 30 days, higher than 46% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 8.3 CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H

Affected products

  • tinyhumansai openhuman

Classification

Weakness
  • CWE-1427 Improper Neutralization of Input Used for LLM Prompting

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of tinyhumansai/openhuman published their own advisory on GitHub. Reviewed sources take precedence over it.