Security audit

Voice Call

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent voice-call plugin; its sensitive behavior is expected for making calls, but users should understand that call data goes through configured telephony providers and may be logged.

Install only if you intend to let OpenClaw place or handle calls through your configured provider. Verify the publisher before entering Twilio/Telnyx/Plivo credentials, obtain consent before calling people, avoid secrets or regulated data in calls unless approved, and review settings for inbound policy, webhook exposure, sessionScope, call-log store, and signature verification.

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: 92% confidence
Finding: This skill enables outbound voice calls through third-party telephony providers but does not warn users that phone numbers and message content will be transmitted off-platform to external services such as Twilio, Telnyx, or Plivo. That omission can lead to unintended disclosure of personal data, sensitive message content, and compliance/privacy issues, especially because the skill is specifically designed to send user-supplied content to external providers.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: dist/.setup/runtime-entry-YWSSnAsH.mjs:1795
Evidence: const proc = spawn("ngrok", args, {