CVE-2026-54141
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.
AI analysis
Not analysed yet.
Claude analyses new vulnerabilities after each morning's collection, most important first, up to a daily limit. The verified data on this page is complete without it.
The sources do not list affected products or versions for this vulnerability yet.
0.8%55th percentile
Bar shows rank among all scored CVEs.
Published
First publication at the source
Collected
First seen by Baba Yaga Security
Last modified
Latest change at the source