The Agent Skills Directory

[SAFE]: The skill's functionality aligns perfectly with its stated purpose of providing a Home Assistant interface using official and documented API endpoints.
[COMMAND_EXECUTION]: The skill utilizes the curl binary to communicate with the Home Assistant server, which is a standard and appropriate method for this type of integration.
[PROMPT_INJECTION]: This skill has the following profile regarding indirect injection risks:
Ingestion points: User-provided text and Home Assistant responses are processed in SKILL.md.
Boundary markers: Not explicitly present in the curl command demonstration.
Capability inventory: Uses curl for network requests.
Sanitization: Relies on the underlying agent runtime and the Home Assistant API's internal intent parsing; no specific sanitization is implemented in the skill description itself.

homeassistant-assist