Log in Start free

Vulnerability · Published Nov 5, 2026 · Assigned by GitHub_M

CVE-2026-54141OpenHuman: Yuanbao non-web channel can bypass human approval to execute `node_exec`

Critical 9.0

In plain English

A critical-severity code injection in openhuman from tinyhumansai. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.8% (higher than 56% of all known vulnerabilities).

Severity (CVSS 3.1)9.0Critical
Exploit odds (30 days)0.8%top 44.5% of all CVEs
Exploited in the wildNo reportsnot in CISA KEV
Attack toolingNoneno public tooling known

Official description

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.

Affected products (as reported)

VendorProductVersions
tinyhumansai openhuman < 0.57.13

Weakness: CWE-94, CWE-862 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:H

References