ClawHub
Back to skill

Security audit

Book Color

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Lokuli booking helper with expected external booking and contact-data use, but users should confirm before sharing personal details or creating an appointment.

Install only if you intend to use Lokuli for color-service search and booking. Before creating a booking, confirm the provider, service, time, and that you are comfortable sending your name, email, phone number, ZIP code, and appointment details to Lokuli.

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 collects and sends sensitive personal data including name, email, phone number, and appointment details to an external MCP service, but the skill text does not warn the user that this transmission will occur. Without clear disclosure and consent, users may unknowingly provide personal data to a third party, creating privacy, compliance, and trust risks.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger language is broad enough that the skill may activate on generic 'color service request' phrasing without clear user intent to use this specific external booking workflow. That can cause unintended invocation of a third-party booking/search flow, increasing the chance of unnecessary data exposure or confusing autonomous actions.

Static analysis

No suspicious patterns detected.