---
id: "CVE-2026-54141"
kind: "vulnerability"
aliases: ["CVE-2026-54141"]
title: "OpenHuman: Yuanbao direct messages can run shell commands without approval"
severity: "critical"
cvss: 9.0
epss: null
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["agent-harness", "ai-tooling", "desktop", "node", "openhuman", "yuanbao"]
not_affected_if: ["no-yuanbao-channel", "node-disabled", "version-0.57.13-or-later"]
published_at: "2026-11-05T17:18:19+00:00"
first_seen_at: "2026-11-05T17:40:04+00:00"
updated_at: "2026-11-05T17:42:07+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-54141", "first_seen_at": "2026-11-05T17:40:04+00:00"}]
exploit_sources: []
---

# OpenHuman: Yuanbao direct messages can run shell commands without approval

OpenHuman is an open-source agent harness; before 0.57.13, a direct message from an outside sender on a configured Yuanbao channel could make the agent run JavaScript and operating-system commands. The approval gate skipped its prompt for these messages, so the commands ran as the OpenHuman user.

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the installed OpenHuman version against `0.57.13`
- Look for a configured Yuanbao channel in OpenHuman's channel settings
- Confirm whether Node is enabled for the agent

## Fix

- OpenHuman: move to `0.57.13` or later

## Timeline

- 2026-11-05T17:40:04+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-54141

## Documents

- [advisory] Vendor advisory: github.com https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-gg3m-wgmq-vhmx
- [fix] Patch: github.com https://github.com/tinyhumansai/openhuman/commit/3a7180da7765af861bf44d79e025fc67dbeae0ca
- [fix] Release notes: github.com https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13

## From the sources

OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, a remote direct message received through a configured Yuanbao channel is converted into a generic channel AgentTurnRequest that uses the default tool policy without establishing an interactive approval context. Under the default Supervised autonomy policy with Node enabled, node_exec is classified as a write operation that should prompt for approval, but ApprovalGate treats missing APPROVAL_CHAT_CONTEXT as a non-interactive turn and allows execution. Because Yuanbao direct messages are open by default, an external sender who can message the connected bot can influence the agent to execute JavaScript and operating-system commands as the OpenHuman user without an approval prompt. The issue requires a configured Yuanbao channel, the default approval-requiring policy state, Node availability, and successful model selection of node_exec. This issue is fixed in version 0.57.13.

---

_Free to read, with fair use of about 60 pages a minute. For higher limits or API access: sales@infrastack.ai_