Back to skill

Security audit

Book IT Support

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Lokuli MCP booking helper for IT-support services, with no local code or persistence, but users should confirm before sending contact details or creating a booking.

Install only if you are comfortable using Lokuli's external MCP service for IT-support search and booking. Before creating a booking, confirm the provider, time slot, and any contact details being sent, especially name, email, and phone number.

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
96% confidence
Finding

The trigger language is overly broad because it activates on essentially any IT-support service request, which can cause the skill to be invoked outside a narrowly expected booking context. In practice, this increases the chance of unintended routing to an external MCP service and unnecessary disclosure of user intent or booking-related data without clear user awareness.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The create_booking example includes personal data fields such as name, email, and phone number, but the documentation does not warn that this information will be transmitted to an external third-party service. This can lead to privacy violations, uninformed consent issues, and accidental exposure of personally identifiable information if users or integrators are not clearly informed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.