Back to skill

Security audit

Book Bartender

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow bartender-booking integration, but it can send personal contact details to an external service and create a booking without explicit consent or confirmation instructions.

Review this skill before installing if you are comfortable with a third-party Lokuli MCP service receiving booking details such as your name, email, phone number, zip code, date, and selected provider. Only use it when you intend to make a bartender booking, and require explicit confirmation before any create_booking call.

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
97% confidence
Finding

The skill facilitates transmission of personal contact data such as name, email, and phone number to an external MCP endpoint, but the description provides no warning or consent cue to the user. This creates a meaningful privacy and data-sharing risk because users may not realize their PII will be sent off-platform to complete a booking.

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 generic requests like finding or booking a bartender without clear scoping, confirmation, or guardrails. That can cause the skill to engage in situations the user did not explicitly intend, increasing the chance of unintended third-party lookups or booking flows involving external services.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.