Back to skill

Security audit

Book Pressure Washing

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says by helping book pressure-washing through Lokuli, but it is too broad about when it activates and does not clearly require consent before sending contact details to an external booking service.

Review before installing. Use this only if you are comfortable with an agent contacting Lokuli's MCP service and potentially sending your name, email, phone number, ZIP code, selected provider, service, and time slot. Confirm the provider and booking details before allowing any booking to be created.

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 describes booking through an external MCP endpoint and includes fields for customer name, email, and phone, but it does not warn users that this personal information will be transmitted to a third-party service. In this context, the omission is significant because the skill is specifically designed to handle bookings, making collection and external disclosure of PII a core part of its operation.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger description is broad enough to match generic pressure-washing requests without clearly constraining the action to discovery versus booking. This can cause the skill to activate in situations where the user did not explicitly intend to use an external booking workflow, increasing the chance of unintended tool use and downstream data sharing.

Static analysis

No suspicious patterns detected.