home-assistant-best-practices

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation for integrations and dashboard cards from the official Home Assistant GitHub repository (github.com/home-assistant/home-assistant.io). These downloads are from a well-known service and are used exclusively for providing up-to-date documentation to the agent.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it analyzes and modifies Home Assistant configuration data which may originate from untrusted or external sources.
  • Ingestion points: Home Assistant YAML configuration files, entity registry data, and dashboard JSON retrieved via REST and WebSocket APIs.
  • Boundary markers: No explicit boundary markers or delimiters are instructed for the processed configuration data.
  • Capability inventory: The skill is designed to read and write Home Assistant configuration through its standard APIs. It does not perform arbitrary shell command execution or direct file system access.
  • Sanitization: There are no explicit instructions for sanitizing or validating the content of the configuration data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 08:57 AM