Back to skill

Security audit

Book Piercing

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward piercing appointment booking guide for Lokuli MCP, with external contact-data sharing that users should confirm before use.

Before installing, be aware that using the booking flow may send your name, email, phone number, appointment time, and selected provider details to Lokuli's external MCP service. Confirm searches and bookings explicitly, and avoid providing contact details unless you intend to make an appointment.

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
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
92% confidence
Finding
The trigger text is broad enough to activate on generic 'piercing' requests, not just explicit booking intent. In a skill that can search providers and create bookings through an external MCP endpoint, overbroad routing can cause the assistant to invoke the skill in contexts where the user only wanted information, increasing the chance of unintended external data sharing or transactional actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill includes a create_booking flow that sends personal data such as name, email, and phone number to a third-party MCP service, but the skill text does not warn users about this external transmission. Without clear disclosure and consent, users may unknowingly provide sensitive contact information to an external provider, creating privacy, compliance, and trust risks.

Static analysis

No suspicious patterns detected.