The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses powershell -ExecutionPolicy Bypass to run a configuration script on Windows systems, which bypasses local script execution policies.
[COMMAND_EXECUTION]: User-provided data (hostname, username, password) is interpolated directly into shell and PowerShell command strings. Without explicit sanitization instructions, this creates an attack surface for command injection if a user provides malicious input.
[CREDENTIALS_UNSAFE]: The skill passes administrative credentials, including local admin passwords and experimental API keys, as plaintext command-line arguments to scripts. Command-line arguments are typically visible to other users on the system via process monitoring tools and may be stored in shell history files.

setup