homey-cli
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Homey hubs, including device names, zone names, and status reports. This represents an attack surface where maliciously crafted strings within the home automation environment could influence the agent's behavior.
- Ingestion points: Device lists, flow lists, and status updates retrieved via
run.sh(SKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are documented.
- Capability inventory: The skill possesses the ability to execute shell commands via
bash run.shand perform network operations to the Homey API. - Sanitization: No explicit sanitization or validation of the retrieved hub data is mentioned in the instructions.
- [EXTERNAL_DOWNLOADS]: The setup process involves running
npm install, which downloads external dependencies from the Node Package Manager registry. - [COMMAND_EXECUTION]: The skill uses a wrapper script
run.shto execute various operations including authentication, device control, and system inspection.
Audit Metadata