ClawHub
Back to skill

Security audit

Walkie-Talkie Mode

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed voice-to-voice WhatsApp helper that locally transcribes audio and generates speech replies, with no evidence of hidden sharing, persistence, or destructive behavior.

Install only if you want incoming voice messages handled as prompts and converted to text/audio locally. Be mindful that voice notes may contain sensitive information, and review generated replies before sending when your client allows it.

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
88% confidence
Finding
The skill automatically transcribes incoming WhatsApp voice messages and processes their contents, but it does not clearly warn users about that data handling behavior. This can undermine informed consent and privacy expectations, especially because voice notes may contain sensitive personal, financial, or health information that users may not expect to be automatically converted to text and processed.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.