open-terminal-guide
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The documentation describes endpoints for shell command execution (
/execute), interactive PTY sessions (/api/terminals), and Jupyter notebook cell execution. These features are the primary intended functions of the Open Terminal tool, designed to provide agents with a controlled execution environment. - [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the Open Terminal software using standard package managers (
pip,uvx) and pulling container images from the official GitHub Container Registry (ghcr.io/open-webui/open-terminal). It also documents a file upload feature that allows the server to fetch content from remote URLs, though it includes warnings against using this for untrusted sources. - [SAFE]: The documentation includes multiple dedicated security guardrail sections across all reference files. These sections advise users to deploy the service behind a VPN, use Docker for process isolation, pin container images by digest, and avoid hardcoding API keys. It also correctly instructs the agent to treat all user-supplied commands and remote URLs as untrusted input.
Audit Metadata