ClawHub
Back to skill

Security audit

Book Oil Change

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow oil-change booking helper that uses an external Lokuli MCP service, with no local code execution or persistence, though users should notice that bookings may send contact details to Lokuli.

Install this only if you are comfortable using Lokuli's external MCP service for oil-change search and booking. Before creating a booking, confirm the provider, service, time slot, and that your name, email, and phone number will be sent for the reservation.

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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger text is overly broad because it activates on effectively any oil-change-related request, increasing the chance the skill runs without sufficiently specific user intent. In a booking skill that can reach an external MCP endpoint and potentially progress toward a reservation, over-triggering can lead to unintended tool use, privacy exposure, or accidental transaction flow initiation.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill facilitates sending customer name, email, and phone number to an external Lokuli MCP service, but the description does not warn the user that their personal contact information will leave the local assistant environment. This lack of transparency undermines informed consent and can cause unexpected disclosure of sensitive personal data to a third party.

Static analysis

No suspicious patterns detected.