Book Physical Therapy

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple physical-therapy booking helper that discloses its Lokuli endpoint and expected booking fields, with no hidden code or persistence.

Install only if you are comfortable using Lokuli for physical-therapy search and booking. Before creating an appointment, confirm the provider, service, time, and exact contact details that will be sent, and avoid sharing unnecessary medical details beyond what is needed to book.

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 text is broad enough to activate on general physical-therapy requests, which can cause the agent to invoke an external booking workflow before the user has clearly asked to search or book through this provider. In this context, the skill connects to a third-party MCP endpoint and can progress toward appointment booking, so over-triggering increases the risk of unintended external data disclosure or transactional actions.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly supports sending customer name, email, and phone number to an external MCP service, but it does not warn that this is privacy-sensitive data or require explicit user consent immediately before transmission. Because this is healthcare-adjacent booking, users may share especially sensitive context, and sending contact details to a third party without clear disclosure or confirmation creates meaningful privacy and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal