Back to skill

Security audit

Book Fitness

Security checks across malware telemetry and agentic risk

Overview

This is a simple fitness-booking connector that uses Lokuli’s external MCP service, with personal contact details used only for the expected booking flow.

Install only if you are comfortable using Lokuli as a third-party fitness booking service. Treat searches as external requests, and only provide your name, email, or phone when you intend to make a booking after confirming the provider, service, time, and details to be sent.

SkillSpector

By NVIDIA
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
91% confidence
Finding
The skill description uses very broad trigger language such as 'any fitness service request,' which can cause the agent to invoke this booking workflow in situations where the user only wants general information rather than an external transaction. In a booking skill, overbroad activation increases the risk of unintended use of external tools and unnecessary disclosure of user data during a booking flow.

Missing User Warnings

High
Confidence
97% confidence
Finding
The create_booking example includes transmission of personal contact data including full name, email, and phone number to an external MCP endpoint, but the documentation does not instruct the agent to warn the user or obtain clear consent before sending that information. In this context, the skill directly facilitates third-party data sharing, making the omission materially dangerous because sensitive personal data could be disclosed without informed user approval.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.