Back to skill

Security audit

Book Eyebrows

Security checks across malware telemetry and agentic risk

Overview

This is a simple eyebrow-service booking skill whose external booking endpoint and requested contact details fit its stated purpose, though users should confirm before sending personal information.

Install this only if you want an agent to search and book eyebrow services through Lokuli. Before any booking is submitted, confirm the provider, service, date, time, and the exact name, email, and phone number that will be sent to Lokuli.

SkillSpector

By NVIDIA
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
Confidence
89% confidence
Finding
The trigger description is broad enough to activate on generic 'eyebrows' service requests without clear constraints, which increases the chance the skill is invoked in situations the user did not specifically intend. In a booking workflow tied to an external MCP endpoint, overbroad activation can lead to unnecessary data collection, unintended third-party queries, or steering a user into a transactional flow prematurely.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents collection and transmission of customer name, email, and phone number to a third-party booking endpoint, but provides no user-facing warning, consent language, or privacy notice. This creates a meaningful privacy risk because users may not understand that their personal contact data will be sent off-platform to complete the booking.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.