ClawHub
Back to skill

Security audit

Book Fitness

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward fitness booking connector, with external booking and contact-data use visible in the artifact.

Before installing, be aware that creating a booking through this skill may send your name, email, phone number, booking time, and selected provider/service details to Lokuli's external MCP service. Use it for explicit fitness search or booking tasks and confirm details before booking.

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 includes a create_booking flow that sends customerName, customerEmail, and customerPhone to an external endpoint, but the skill description does not warn that personal contact data will be transmitted off-platform. In a booking context, this omission can undermine informed consent and cause privacy harm if the skill is invoked unexpectedly or users are not clearly told what data is shared.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger language is broad enough to activate on generic fitness-related requests without clearly limiting scope to explicit booking or provider-search intents. That increases the chance the skill is invoked in contexts the user did not intend, which can lead to unnecessary collection or transmission of booking-related data to an external MCP service.

Static analysis

No suspicious patterns detected.