ClawHub
Back to skill

Security audit

Book Art Lessons

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward art-lesson booking helper that uses an external Lokuli MCP endpoint and does not include local code, persistence, or hidden behavior.

Before installing, understand that searches and bookings use Lokuli's external MCP service. Only provide name, email, and phone when you intend to create a booking, and confirm the provider, service, time slot, and contact details before submission.

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 documents collecting and sending customerName, customerEmail, and customerPhone to an external MCP endpoint, but it does not warn that this personal data will leave the local agent environment. This creates a privacy and consent risk because users may not understand that booking uses a third-party service and transmits personally identifiable information off-platform.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger text is broad enough to activate on generic service-seeking requests, which can cause the agent to invoke this skill in situations the user did not specifically intend. In a booking workflow, overbroad invocation increases the chance of unnecessary third-party queries and can steer users into external transactions without sufficiently clear scoping.

Static analysis

No suspicious patterns detected.