ClawHub
Back to skill

Security audit

voice-call

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed wrapper for a voice-call plugin, with real-call risks users should confirm before use.

Install only if you intend agents to place or manage voice calls. Before live use, configure a mock provider for testing where possible, require explicit confirmation for real outbound calls, and ensure you have consent to call recipients because provider metadata and message content may be handled by telephony services and may incur 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
  • 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
94% confidence
Finding
The skill enables agent-initiated outbound phone calls through third-party telephony providers, but the description and usage guidance do not prominently warn users that real calls may be placed externally and may incur privacy, consent, and billing consequences. This can lead to accidental calls to real recipients, unintended disclosure of message contents to providers, or surprise charges when the agent uses the tool without the user appreciating its real-world effect.

Static analysis

No suspicious patterns detected.