Security audit

Voice Call

Security checks for vulnerabilities and agentic risk

Overview

The plugin is coherent for voice calling, but it lets agents place real phone calls through third-party providers without an explicit confirmation or consent guardrail in the skill instructions.

Install only if you want agents to be able to initiate real outbound calls. Prefer mock mode while testing, require your own user confirmation workflow before real calls, avoid sending sensitive content in messages, and review provider credentials, webhook exposure, inbound policy, sessionScope, and call-log retention before enabling Twilio, Telnyx, or Plivo.

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 agent-initiated phone calls through external providers (Twilio, Telnyx, Plivo) but does not warn about external network use, disclosure of call content to third-party providers, or the privacy and consent implications of contacting real phone numbers. In an agent setting, this omission can lead to unintended outreach, leakage of sensitive information in spoken messages, and user surprise or policy violations if the agent places calls without clear notice and confirmation.
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, {