ClawHub
Back to skill

Security audit

voip-manager

Security checks across malware telemetry and agentic risk

Overview

This is a sparse but coherent VoIP skill with expected API-key use and no hidden code or malicious behavior shown.

Install only if you know which VoIP provider and script you intend to use. Use a dedicated least-privilege API key, keep it out of prompts and logs, and require confirmation before placing, ending, forwarding, recording, or otherwise changing calls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill's activation guidance is broad enough that an agent may invoke it for loosely related 'voice' or 'communication' tasks without clear user intent or scope checks. Because this skill can trigger external VoIP operations, ambiguous routing increases the chance of unintended calls or actions being performed in the real world.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs use of a VoIP API key and describes external VoIP operations, but it does not warn users that the skill may interact with third-party services, consume paid resources, or initiate communications. This omission can lead to unsafe deployment, accidental credential misuse, and unanticipated external actions with financial and privacy consequences.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal