Security audit

Voice Call

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent voice-calling plugin, but installing it lets OpenClaw place and manage real phone calls through configured telephony providers.

Install only if you want OpenClaw to make or handle phone calls. Configure provider credentials carefully, keep webhook signature verification enabled in production, avoid putting sensitive content in call messages unless necessary, and require explicit user confirmation before agents place live outbound calls.

SkillSpector

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: 94% confidence
Finding: The skill enables outbound voice calls through external telephony providers and the documented examples include transmitting a destination phone number and spoken message content, but it does not warn users that this data leaves the local system and is sent to third-party services such as Twilio, Telnyx, or Plivo. This creates a privacy and consent risk because an agent or user may unknowingly disclose sensitive personal data or confidential message content to external providers and trigger real-world calls.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: dist/runtime-entry-Ln4SWaYK.js:1642
Evidence: const proc = spawn("ngrok", args, {