ClawHub
Back to skill

Security audit

Book Salon

Security checks for vulnerabilities and agentic risk

Overview

This is a simple salon-booking skill that openly uses Lokuli's external MCP endpoint, but users should be careful because booking requires sending contact details to that service.

Install only if you are comfortable using Lokuli's external MCP service for salon searches and bookings. Before any booking is created, confirm the salon, service, time slot, and the contact details being sent.

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 booking via an external MCP endpoint and the booking example includes personal data such as name, email, and phone number, but it does not warn that this information will be transmitted to a third-party service. In this context, omission of that disclosure is risky because users may provide sensitive contact data without informed consent, creating privacy, compliance, and trust issues.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger language is broad enough to activate on generic salon-related requests, not just clear booking intent. That can cause the agent to route ordinary informational queries into an external booking workflow, increasing the chance of unnecessary external calls and downstream collection or transmission of user data without sufficiently specific user intent.

Static analysis

No suspicious patterns detected.