ClawHub
Back to skill

Security audit

Book Pilates

Security checks for vulnerabilities and agentic risk

Overview

This skill is meant for Pilates booking, but it can send personal contact details to an external Lokuli booking endpoint without explicit consent or clear activation limits.

Review this before installing if you are comfortable with a Lokuli MCP service handling booking searches and reservations. Users should confirm the exact class, provider, time, and contact details before any booking call, and should be told that their personal information will be sent to Lokuli to complete the reservation.

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
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill sends sensitive personal data such as name, email, phone number, and booking details to an external MCP endpoint, but the skill text provides no warning, consent step, or privacy notice. In this context, that omission is especially risky because the tool is expressly designed to create bookings with third-party providers, so users may not realize their personal information is being transmitted outside the assistant environment.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text is broad enough to activate on general pilates-related requests, not just clear booking intent. That can cause the agent to invoke an external booking workflow unnecessarily, increasing the chance of unintended actions or premature collection/transmission of user data to a third-party service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.