Back to skill

Security audit

Book Garage Door

Security checks for vulnerabilities and agentic risk

Overview

This garage-door booking skill is coherent, but it can send a user's contact details to Lokuli and create a booking without clear consent or confirmation instructions.

Review before installing. Use it only when you are comfortable sending your name, email, phone number, ZIP code, and booking details to Lokuli, and require the agent to confirm the provider, time slot, and contact fields with you before creating any booking.

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 exposes a booking flow that collects and transmits personal contact information (name, email, phone) to an external MCP endpoint without any user-facing warning, consent language, or data-handling notice. This is dangerous because users may disclose sensitive personal data without understanding it will be sent to a third-party service, creating privacy, compliance, and trust risks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description includes a broad catch-all phrase ('or any garage-door service request'), which can cause the skill to activate on loosely related requests without clear user intent. Over-broad activation increases the chance of unintended tool use, unnecessary data collection, or steering the conversation into booking flows when the user only wanted general information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.