Home Assistant Agent (Secure)
Security checks across malware telemetry and agentic risk
Overview
This skill is transparent about using a Home Assistant token to send smart-home commands through Home Assistant Assist, with no hidden code or install-time execution found.
Install only if you are comfortable giving OpenClaw controlled access to Home Assistant. Use a dedicated non-admin Home Assistant user with limited area/entity access, protect and rotate the long-lived token if exposed, disable trusted-network login bypass if enabled, and remove curl's -k option when your Home Assistant certificate is trusted.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.