ClawHub
Back to skill

Security audit

Booking.com — Complete Toolkit

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Booking.com/StayingAPI read-only travel data integration, with ordinary API-key handling and no hidden or destructive behavior found.

Install this if you want a broad StayingAPI-backed Booking.com travel-data tool. Use a sandbox key for evaluation, store live keys only in a trusted secret store or protected environment file, and choose a focused skill instead if you only need one narrow Booking.com function.

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 guidance says to use the skill for essentially 'any Booking.com data task,' which is broader than necessary and can cause an agent to invoke this high-scope skill even when a narrower or local capability would suffice. In practice this increases unnecessary external calls, expands data exposure to a third-party service, and raises the chance of acting on ambiguous user intent.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The guide explicitly tells the user to persist `STAYINGAPI_KEY` across future sessions but does not warn about least-privilege storage, shell history leakage, file permissions, or using a platform secret store. Persisting API credentials in shell profiles or general config files can expose the key to other local users, logs, backups, or unintended tooling that reads environment files.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.