ClawHub
Back to skill

Security audit

voiceskill123

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward voice-call helper, but live provider use can place real phone calls and incur provider charges.

Install only if you intend agents to initiate voice calls. Use the mock provider for testing, review live provider credentials and from-number configuration, and require confirmation before any real outbound call to avoid unintended third-party contact or charges.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill enables agent-initiated outbound voice calls through real telephony providers, but the description and usage guidance do not clearly warn users that actions may trigger real-world phone calls and possible charges. This can lead to unintended contact with third parties, privacy issues, and financial cost, especially because the tool exposes direct call-initiation actions and supports production providers such as Twilio, Telnyx, and Plivo.

Static analysis

No suspicious patterns detected.