ClawHub
Back to skill

Security audit

Voice Call

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only skill for placing or checking voice calls through an already-enabled plugin; the main risk is that live calls can contact real people, cost money, and send message content to telephony providers.

Install only if you intentionally use the voice-call plugin. Prefer mock mode for testing, keep telephony credentials restricted, confirm the destination number and message before live calls, avoid sensitive content unless necessary, and use allowlists or approval steps for calls to real recipients.

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
89% confidence
Finding
The skill explicitly enables agent-initiated outbound voice calls and provides concrete invocation examples, but it does not warn about consent, call charges, telephony abuse, or the privacy implications of sending spoken messages to phone numbers. In an agent ecosystem, this omission increases the risk of unauthorized calls, social engineering, and accidental disclosure of sensitive information through a paid external channel.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.