ClawHub
Back to skill

Security audit

TravelHound

Security checks across malware telemetry and agentic risk

Overview

This is a travel search/planning skill that uses an external CLI for live booking data, and its behavior is disclosed and aligned with that purpose.

Only install if you are comfortable with an external flyai/Fliggy-backed CLI receiving travel search details and returning booking links. Confirm before allowing any global npm install, and avoid using it for casual travel discussion unless you intend live searches.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The invocation guidance includes broad natural-language travel phrases such as 'cheap flights to', 'hotels in', and 'plan a trip to', which can appear in ordinary conversation rather than clear tool-invocation requests. In an agent environment, this can cause unintended activation of a browser-driven skill, leading to unnecessary navigation, data collection, or execution of downstream actions when the user may have only been asking a general question.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list contains very generic multilingual tokens like '机票', '酒店', 'trip to...', and 'travel to...', which are too vague to reliably distinguish skill invocation from ordinary discussion. Because the skill uses browser navigation against live travel sites and integrates with other skills, accidental routing could expose user queries to external services or trigger unnecessary automated browsing with minimal user intent.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list contains very broad, common travel terms such as "travel," "hotel," "vacation," and similar Chinese equivalents, which can cause the skill to activate for generic user requests that may not be intended for this package. Overbroad activation increases the chance of unsolicited invocation, accidental data handling, or user confusion, especially because the skill covers multiple travel functions and comparison workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.