Guide safe use of code_execution_remote for shell-backed execution on the connected A0 CLI host. Use when the user asks for their computer, local terminal, CLI host, remote shell, not Docker, or host-side Python/Node/terminal commands.
76
95%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Use code_execution_remote only for shell-backed execution on the machine where A0 CLI is running. Shells, runtimes, and paths belong to the CLI host, not the Agent Zero server or Docker container.
If the task belongs inside Agent Zero's own runtime, use the normal server-side execution tool instead.
Browser boundary: do not use shell launchers such as xdg-open, sensible-browser, open, start, or Python webbrowser.open as a fallback for requests to use/control/open a page in the host browser. Use the browser tool instead; if it reports missing Chrome remote-debugging consent, stop and relay the chrome://inspect/#remote-debugging instructions.
terminal, python, and nodejs.runtime=output and runtime=reset remain available for existing sessions.runtime=terminal for shell commands, runtime=python for Python snippets, and runtime=nodejs for Node.js snippets.session while continuing a workflow; session state is local to the CLI frontend.runtime=output when a previous command is still running or returned before the shell reached a prompt.runtime=reset when a session is stuck and no replacement command needs to run yet.reset: true with runtime=terminal, python, or nodejs when a session is stuck and the next command should run immediately in a clean shell.391fab9
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.