Back to skill

Security audit

Book Painter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent painter-booking helper, but users should know it uses Lokuli's external MCP service and may send contact details when creating a booking.

Before installing, understand that booking through this skill relies on Lokuli's external MCP service. Confirm details before creating a booking, and only provide name, email, and phone when you intend to send them for that booking.

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
98% confidence
Finding

The skill describes booking via Lokuli's external MCP endpoint and includes a create_booking tool that transmits customerName, customerEmail, and customerPhone, but it does not warn the user that their personal contact information will be sent to a third-party service. This lack of transparency can lead to uninformed consent and privacy/security risk, especially because the skill facilitates direct transmission of PII off-platform.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger text is overly broad because it claims to activate on "any painter service request," which can cause the skill to be invoked for vague or unintended user queries. In a booking skill that can search providers and create bookings through an external MCP service, overbroad activation increases the chance of unintended tool use and unnecessary disclosure of user data during a transactional flow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.