ClawHub
Back to skill

Security audit

Barog

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real clinic-booking helper, but it sends booking details to external services without a clear confirmation step and includes embedded API tokens.

Review before installing. Use it only if you are comfortable sending clinic appointment details, and possibly a phone number, to the BeautsGO-related booking service. The publisher should add an explicit confirmation before each booking submission and move API tokens out of the public skill artifact.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The skill metadata and documentation present the capability as a clinic information/booking helper, but the declared behavior includes submitting appointment data to external APIs, opening external pages, and providing download links. This mismatch is security-relevant because it can mislead reviewers and users about data flows and side effects, especially where personal information may be collected and transmitted off-platform.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The booking flow transmits personal data, including contact information and appointment details, to an external API without a clear prior disclosure or explicit consent step at submission time. This increases privacy and compliance risk because users may provide phone numbers and scheduling data without understanding that the information is being sent to a third-party backend.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
api/skill.js:25