Security audit

Voice Call

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent voice-call plugin that can place real phone calls when configured with a telephony provider, so users should treat it as a real-world calling tool rather than a simulator.

Install this only if you want OpenClaw agents to place and manage real phone calls. Use mock mode for development, configure real providers carefully, protect telephony credentials, and consider host-level confirmations or allowlists before letting agents call arbitrary numbers.

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

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly enables outbound phone calls through real telephony providers (Twilio, Telnyx, Plivo) but does not clearly warn that using the tool may trigger real-world external calls, costs, and contact with unintended recipients. In an agent setting, this omission can lead to accidental dialing, privacy issues, spam/abuse scenarios, or financial charges if users or downstream agents assume the action is only simulated.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: dist/.setup/runtime-entry-BNOQRXii.mjs:1649
Evidence: const proc = spawn("ngrok", args, {