CVE-2026-54143 · AI agents & MCP
NO FIX YET · SEE WHAT TO DO
OpenHuman is an open-source agent harness that runs as a desktop app and Rust library. Before 0.57.13, a message sent through a configured external channel can make the agent create cron jobs that run shell commands as the OpenHuman user, without human approval.
first public Oct 9, 2026 · 1 source
Check it with your coding agent
It checks your repository and tells you if you’re affected, with the fix.
Teams running OpenHuman with an external messaging channel connected to the agent are exposed, because inbound messages can drive the agent's scheduling. Desktop or local-only installs without an external channel are less exposed. The sources do not say which channel types are involved.
Not affected if no-external-channel, version-0.57.13-or-later
Who cares ai-agents, desktop, openhuman, rust
0.57.13.0.57.13 or later.OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before version 0.57.13, an attacker who can send messages to a configured external channel can cause the agent to create persistent shell cron jobs without human approval. The scheduler later executes these jobs with the privileges of the OpenHuman runtime user. Command validation also permits leading environment assignments that can redirect allowed commands to executable helpers. The demonstrated exploit requires a suitable helper executable already present on the host. This can lead to unauthorized persistent command execution and compromise data and resources accessible to OpenHuman. This issue is fixed in version 0.57.13.
Are you affected?
Tell InfraStack what you run. It checks this one, and every next one, against your stack.
Ask from here. InfraStack checks the affected versions against your stack and answers in your inbox.
InfraStack checks the affected versions against your stack and answers in Slack, with the evidence and the fix.
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.