ClawHub
Back to skill

Security audit

VoiceMonkey

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward VoiceMonkey skill for user-directed Alexa announcements, routines, flows, and media, with the main caution being careful handling of the API token.

Install only if you trust the agent to use your VoiceMonkey token and control the Alexa devices tied to that account. Prefer the Authorization-header examples over putting tokens in URLs, avoid sharing shell history or logs that may contain the token, rotate the token if exposed, and require explicit confirmation before triggering routines, flows, websites, or loud announcements.

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
97% confidence
Finding
The skill includes a curl example that places the secret VoiceMonkey token directly in the URL query string. Query parameters are commonly exposed in shell history, proxy logs, browser history, monitoring systems, and server access logs, so users may unintentionally leak a credential that can control Alexa devices, trigger routines, or start flows. In this skill context, the token is high-value because it authorizes remote actions on home/office voice devices, making accidental disclosure more dangerous than a generic API example.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.