Back to skill

Security audit

Book Mechanic

Security checks for vulnerabilities and agentic risk

Overview

The skill matches a mechanic-booking purpose, but it can create an external booking with personal contact details and its trigger is broader than clear booking intent.

Review this skill before installing. Use it only when you intend to search for or book mechanic services through Lokuli, and confirm the provider, time slot, and contact details before allowing a booking request to be sent.

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
Confidence
97% confidence
Finding
The skill documents collection and transmission of customer name, email, and phone number to an external MCP endpoint but does not warn the user or require explicit consent. This creates a meaningful privacy and data-handling risk, especially if the skill is triggered unexpectedly or users do not realize their personal contact information is being sent off-platform.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger text is broad enough to activate on general mechanic-related requests rather than clearly scoped booking intent. In this skill, accidental activation matters because it can route users into an external booking workflow and potentially collect or transmit personal data without sufficiently explicit user intent.

Static analysis

No suspicious patterns detected.