ha-repairs
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides guidelines for the Home Assistant Repairs feature, focusing on user notifications for actionable issues.
- [SAFE]: All code snippets leverage standard Home Assistant core helpers and registry functions.
- [SAFE]: No malicious patterns such as credential theft, remote code execution, or prompt injection were detected.
- [SAFE]: Regarding indirect prompt injection surfaces: 1. Ingestion point: external data from self.client.async_get_data() in coordinator.py; 2. Boundary markers: Absent; 3. Capability inventory: ir.async_create_issue in coordinator.py; 4. Sanitization: Absent. These findings do not escalate the verdict.
Audit Metadata