Wyoming Clawdbot

Security checks across malware telemetry and agentic risk

Overview

This bridge appears purpose-built, but it exposes a user’s Clawdbot session to network-received voice prompts unless carefully isolated.

Install only on a trusted, firewalled host. Restrict the listening address or firewall port 10600 so only Home Assistant can reach it, consider a dedicated low-privilege Clawdbot profile, make the .clawdbot mount read-only if possible, and reduce or rotate logs because spoken requests and responses may be recorded.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The README explicitly states that spoken text is sent from Home Assistant through this bridge to Clawdbot, but it does not warn users that voice-derived content may leave the local Home Assistant environment and be processed by an external AI service. In a voice-assistant context, users may unknowingly transmit sensitive household, personal, or authentication-related information, so the missing privacy disclosure is a real security/privacy weakness.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal