Back to skill

Security audit

Book Waxing

Security checks for vulnerabilities and agentic risk

Overview

This booking skill is mostly coherent, but it can route broad waxing requests into an external booking flow that sends contact details without clearly requiring user confirmation.

Install only if you are comfortable using Lokuli's external MCP service for waxing searches and bookings. Before any booking is created, the agent should confirm the provider, service, date/time, and that your name, email, and phone may be sent to Lokuli.

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)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill instructs use of an external MCP endpoint for booking and includes fields for customer name, email, and phone, but does not warn that this personal data will be transmitted to a third-party service. That omission undermines informed consent and can expose users to privacy and compliance risks if sensitive contact data is sent off-platform unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language is broad enough to activate on essentially any waxing-related request, without clearly constraining whether the user wants discovery, comparison, or an actual booking workflow. In a booking skill, overbroad activation can cause the agent to route users into an external transaction flow prematurely, increasing the chance of unintended data sharing or unauthorized booking actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.