hass-cli

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill demonstrates a strong security posture by explicitly forbidding the exposure of sensitive authentication tokens (HASS_TOKEN, HASS_SUPERVISOR_TOKEN) and environment variables. It advocates for sanitized error reporting and read-only discovery steps.
  • [COMMAND_EXECUTION]: The skill facilitates the use of the hass-cli command-line tool. It mitigates command injection risks by requiring the agent to verify syntax using help commands (--help) for the specific installed version rather than relying on cached knowledge.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from Home Assistant commands. It manages this attack surface by:
  • Ingestion points: Data enters the context via hass-cli output (SKILL.md).
  • Boundary markers: None explicitly defined in the prompts, though the skill recommends structured JSON/YAML output for easier parsing.
  • Capability inventory: The skill uses hass-cli for service calls, state changes, and supervisor operations.
  • Sanitization: Instructions include sanitizing errors and avoiding the printing of secrets retrieved during command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:16 PM
Security Audit — agent-trust-hub — hass-cli