The Agent Skills Directory

[DATA_EXPOSURE]: The skill requires environment variables HA_URL and HA_TOKEN for Home Assistant integration. The setup instructions correctly advise verifying these in the active runtime and choosing low-risk targets for initial testing, which aligns with security best practices for credential management.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input describing systems or processes to be suspended.
Ingestion points: User-supplied system/process/notification channel descriptions via the /sleep command.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt template.
Capability inventory: The skill references Home Assistant (HA_TOKEN) and curl for potential integration actions, though the primary instructions focus on designing a plan.
Sanitization: No input validation or sanitization logic is described.

sleep