ClawHub
Back to skill

Security audit

voiceskill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward voice-call helper, but users should treat calls as real third-party communications.

Install only if you intend to let OpenClaw place or inspect calls through a configured telephony provider. Confirm the recipient phone number and message before real calls, avoid sensitive or regulated content unless necessary, and remember provider credentials, phone numbers, call metadata, and spoken message content may be handled by Twilio, Telnyx, Plivo, or the configured provider.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
95% confidence
Finding

The skill enables outbound voice calls through external telephony providers and instructs users to supply a phone number and message, but it does not clearly warn that this data will be transmitted to third-party services such as Twilio, Telnyx, or Plivo. This can lead to unintentional disclosure of personal data, sensitive message content, or regulated information, especially when an agent uses the tool on a user's behalf.

Content

No source excerpt is available for this finding.