home-assistant-api
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of state data and attributes from Home Assistant entities which could potentially contain malicious instructions if the data source is compromised.
- Ingestion points: Data is retrieved from
GET /api/statesandGET /api/states/{entity_id}endpoints, as documented inresources/state-management.mdandresources/examples.md. - Boundary markers: The skill lacks explicit instructions or delimiters to help the agent distinguish between data and potential instructions embedded within entity values.
- Capability inventory: The skill demonstrates significant capabilities including device control (locks, climate, power) and system management (restarting the host) via
POST /api/services/as detailed inresources/service-reference.md. - Sanitization: The provided examples do not include sanitization, validation, or filtering logic for data processed from API responses.
Audit Metadata