Back to skill

Security audit

Book Eyebrows

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent eyebrow-service booking helper, but it can create third-party bookings with personal contact details without explicit consent or confirmation instructions.

Review before installing. Use this skill only if you are comfortable with an agent contacting Lokuli to search and book services, and make sure the agent asks before sending your name, email, phone number, and final booking choice.

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
94% confidence
Finding

The trigger language is broad enough to activate on a wide range of generic 'eyebrows' requests, which can cause the skill to run when the user did not clearly intend to search or book through this third-party service. In a booking skill, over-triggering is security-relevant because it can prematurely steer users into data collection and external transmission workflows.

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 customer name, email, and phone number for transmission to an external MCP endpoint, but it does not warn the user or require clear consent before gathering and sending that personal information. This increases privacy and compliance risk, especially because the skill directly facilitates disclosure of contact data to a third-party service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.