ClawHub
Back to skill

Security audit

Book Party

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed booking workflow for Lokuli party services, with expected but privacy-relevant sharing of contact details during booking.

Before installing, understand that searches and bookings go through Lokuli's external MCP service. Only use it when you intend to search for or reserve party services, and confirm the provider, time slot, name, email, and phone number before creating a booking.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill supports creating bookings with customer name, email, and phone number, but it does not warn that this personal information will be sent to an external service at lokuli.com. In a booking context, this omission undermines informed consent and increases the risk of privacy violations, especially if the skill is triggered automatically or used before the user understands data-sharing implications.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger text is broad enough to activate on loosely related 'party' requests, which can cause the skill to run in situations the user did not clearly intend. In this skill, unintended activation is more dangerous because it can lead users into an external booking workflow and eventual transmission of personal data to a third-party MCP service.

Static analysis

No suspicious patterns detected.