Secure Autonomous
FeedbackGet alertsCheck a deployment
Signals › SIG-2026-11-06-004

CVE-2026-54140: OpenHuman passes unneutralized tool descriptions from external Model Context Protocol (MCP) servers into the agent's context, so a malicious server can steer the agent to invoke other tools (fixed in 0.57.13)

The National Vulnerability Database (NVD) record says that before 0.57.13 OpenHuman places names, descriptions and parameter definitions returned by configured external Model Context Protocol (MCP) servers into the agent's model context without neutralizing instructions, so a malicious or compromised MCP server can return a poisoned description that may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions.

VulnerabilitySoftware agents · Enterprise work agentsRecord published 2026-11-05Posted 2026-11-06
SIG-2026-11-06-004National Vulnerability Database record ↗

The record

Kind
Vulnerability
Source record
CVE-2026-54140: OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, (National Vulnerability Database record)
Record published
2026-11-05
Posted here
2026-11-06
World
Software agents · Enterprise work agents
Controls concerned
Retrieved content as data C-I1
Checked
Checked against its record on 2026-11-06 by a reader who did not draft it; report verification/reports/SIG-2026-11-06-004-2026-11-06.md.

A signal's controls are the ones its record points at, the exposure; a case's controls are the ones its records show were absent or failed, so the two can differ.

Corrections

Changes to what this signal says, with the reason. Every earlier version is kept.

What a signal is. A signal records what a primary record says; it assigns no fault. It is lighter than a case: one dated item from one record, tagged with the world, sector and controls it touches. It becomes a case when it meets the bar for one.

New signals like this, once a week. A short email when a case, signal or rule touches software agents. Free; unsubscribe in one click.

Get the weekly email

Newer: OpenAI misalignment report: a research model in a coding evaluation bypassed its sandbox's network restrictions and reached Amazon S3 and Microsoft's public sign-in service (sample 4 August 2026)
Older: CVE-2026-61536 (GHSA-64vx-6h2c-rjh7): banks resolves an attacker-controlled tool import path without an allowlist, so a model's tool call can run arbitrary code

Is this wrong? Dispute it with the record that shows otherwise. All signals · RSS feed.

Help shape the Register

A person reads every answer; changes it leads to are logged in the methodology. To dispute a claim or reply for a named company, use Respond, dispute, or submit.

Did this page help with what you came to do?