Back to skill

Security audit

Book Dog Trainer

Security checks across malware telemetry and agentic risk

Overview

This looks like a real dog-trainer booking skill, but users should review it because it can send contact details to an external service and create a booking without explicit confirmation instructions.

Install only if you trust Lokuli for dog-trainer bookings. Before allowing use, require the agent to show the selected provider, service, time, price or terms if available, and the exact name, email, and phone number that will be sent, then ask for explicit approval before creating any booking.

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
92% confidence
Finding
The trigger language is broad enough to activate on general dog-trainer-related requests without clear constraints, which can cause the agent to invoke an external booking workflow when the user may have intended only to ask for information or recommendations. Because this skill connects to a third-party MCP endpoint and can progress toward booking, over-triggering increases the risk of unintended external data transmission or action-taking.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill includes a create_booking flow that collects and transmits personal contact information such as name, email, and phone number to an external service, but it does not instruct the agent to warn the user or obtain clear consent before sending that data. In a booking context, this omission creates a privacy and compliance risk because sensitive personal data may be shared with a third party unexpectedly.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.