The Agent Skills Directory

[COMMAND_EXECUTION]: Executes administrative commands on remote Home Assistant instances via SSH, including ha core check for validation, ha core restart for deployment, and log retrieval for verification.
[COMMAND_EXECUTION]: Utilizes the hass-cli utility to interact with the Home Assistant REST API for managing entity states and triggering automation services.
[EXTERNAL_DOWNLOADS]: Facilitates deployment of configuration updates by performing git pull from a user-configured repository or via direct scp transfers for rapid iteration.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by processing external data from system logs, entity states, and YAML/JSON configuration files which could contain malicious instructions.
Ingestion points: Processes output from ha core logs, hass-cli state get, and various configuration files (SKILL.md).
Capability inventory: Possesses capabilities for remote shell command execution via SSH, file transfers via scp, and API service calls via hass-cli (SKILL.md).
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious embedded content within the logs or states it reads.
Sanitization: The skill relies on the official Home Assistant ha core check tool to validate YAML syntax and integrity before applying changes.

home-assistant-manager