Home Assistant Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sensors and device states within the Home Assistant environment, which could potentially contain untrusted content that influences the agent's logic.
- Ingestion points: Data enters the context through entity state monitoring (e.g.,
binary_sensor.alarm,sensor.electricity_usage) and tool outputs fromha_state_get. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore malicious content within sensor data.
- Capability inventory: The skill uses tools (
ha_service_call,ha_automation) to control physical devices, including locks (lock.lock), alarms (alarm_control_panel.home), and cameras. - Sanitization: There is no evidence of sanitization or validation performed on the strings retrieved from the Home Assistant API before they are processed by the agent.
Audit Metadata