ClawHub
Back to skill

Security audit

Book Flooring

Security checks for vulnerabilities and agentic risk

Overview

This is a simple flooring-booking skill that discloses its external MCP endpoint and booking data fields, with no hidden code, persistence, or privilege escalation.

Use this skill only when you want to search for or book flooring services through Lokuli. Before creating a booking, confirm the provider, time slot, and that you are comfortable sharing your name, email, and phone number with the external service.

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
94% confidence
Finding
The trigger description is overly broad because it activates on essentially any flooring-related request, without narrowing scope to booking-specific intent or requiring user confirmation before taking action. In a transactional skill that can search providers and create bookings, broad activation increases the chance the agent invokes the skill in contexts where the user only wanted general information, leading to unintended data collection or booking flow initiation.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill includes a booking flow that transmits sensitive personal contact data such as name, email, and phone number to an external MCP endpoint, but it provides no user-facing warning, consent language, or data-handling notice. This is dangerous because users may not realize their personal information will be sent to a third-party service, creating privacy, compliance, and trust risks if the skill is invoked automatically or without clear disclosure.

Static analysis

No suspicious patterns detected.