The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local setup scripts (check-prereqs.sh, set-env.sh, and PowerShell equivalents) located within the plugin's directory structure to verify the environment and save configuration.
[PRIVILEGE_ESCALATION]: On Windows systems, the skill uses -ExecutionPolicy Bypass to execute prerequisite scripts. This is a common pattern for automated setup tools to ensure functionality across different system configurations.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted user input (hostnames, usernames, and file paths) and interpolates them into shell command arguments.
Ingestion points: User-provided host/IP, username, and absolute paths for credential providers.
Boundary markers: Absent; the skill instructions do not specify delimiters or sanitization for user-provided strings before they are used in bash or powershell commands.
Capability inventory: The skill utilizes Bash and Read tools to execute scripts and inspect existing configuration files.
Sanitization: No explicit sanitization or validation of the user input format is defined in the instructions.

unifi-protect-setup