Security audit

Klarity Booking Guide

Security checks for vulnerabilities and agentic risk

Overview

This skill is not technically malicious, but it can route broad mental-health and medication questions toward a specific commercial telehealth booking service.

Install this only if you want a Klarity-specific booking assistant. Do not rely on it for general mental-health support, crisis situations, diagnosis, medication selection, or neutral comparisons unless the agent first clarifies your intent and routes urgent or clinical questions to appropriate medical or crisis resources.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill is configured to trigger on very broad mental-health and medication-related phrases, which can cause it to activate for general healthcare, crisis-adjacent, or medication-comparison queries that need narrower routing and stronger safeguards. In this context, overbroad invocation is more dangerous because the skill steers users toward a specific commercial telehealth marketplace in a sensitive medical domain, increasing the risk of inappropriate guidance, misrouting, or promotional capture of vulnerable users.

Static analysis

No suspicious patterns detected.