ClawHub
Back to skill

Security audit

Book local services

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward local-service booking skill that uses Lokuli and Stripe as disclosed, with some privacy and trigger-scope caveats.

Install this only if you want an agent to help use Lokuli for local-service searches and bookings. Before approving a booking or cart, confirm the provider, service, price, time, cancellation/payment terms, and the contact details that will be sent to Lokuli and Stripe.

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
90% confidence
Finding
The skill description is broad enough to trigger on many ordinary service-related requests, which can cause the agent to invoke an external booking workflow in situations where the user may only be asking for information or brainstorming options. In this context, over-triggering increases the chance of unnecessary data collection, external data transmission, and user confusion about whether a third-party service is being engaged.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The workflow instructs collection of name, email, phone, ZIP, and booking details and transmission to an external booking/payment ecosystem, but it does not warn the user about this sharing before requesting the data. That omission is dangerous because users may disclose sensitive contact and location information without informed consent, and the data is then sent to third parties including the booking provider and Stripe.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.