Back to skill

Security audit

Book Brake Service

Security checks for vulnerabilities and agentic risk

Overview

This brake-service booking skill is mostly coherent, but it can create a third-party booking while sending a user's name, email, and phone number without explicit consent guidance.

Review before installing. The skill is not malicious, but users should expect queries and booking details to go to Lokuli's MCP service, and should only proceed after confirming the provider, time slot, and personal contact details to be shared.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language is broad enough to activate on generic brake-service-related requests without clearly constraining scope or confirming user intent. In a booking skill that can progress toward third-party actions, overbroad activation increases the chance of unintended invocation and unnecessary data collection or transaction flow initiation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill includes a booking flow that collects and transmits personal contact information to an external MCP endpoint, but it provides no user-facing warning or consent language about sharing name, email, and phone number with a third party. This creates privacy and trust risks because users may not understand that their personal data will be sent off-platform to complete the booking.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.