ClawHub
Back to skill

Security audit

Vocal Chat

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is aligned with its stated purpose of local WhatsApp voice chat and shows no hidden exfiltration, persistence, or destructive behavior.

Install only if you want an agent to process WhatsApp voice messages and send generated replies. Before use, confirm the referenced local speech tools are trusted and understand whether your WhatsApp integration keeps temporary audio, transcripts, or sent voice files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly automates transcription of incoming WhatsApp voice messages and sends generated text/audio replies, but it does not present any user-facing notice or consent warning about this processing. That creates a privacy and transparency risk because users may not realize their audio is being converted to text and used to generate outbound content, increasing the chance of unintended disclosure or non-consensual processing.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.