ClawHub

Budget Traval Plan

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only budget travel helper whose external searches and travel-plan output match its stated purpose.

Use this skill only with a trusted FlyAI travel-search integration, since your travel preferences may be sent to that provider. Treat prices and booking links as suggestions and verify dates, totals, cancellation terms, and provider legitimacy before purchasing.

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
91% confidence
Finding
The manifest description is broad enough to match many ordinary travel-related requests, which can cause the skill to activate outside its intended niche of 'random budget deals.' Overbroad triggers increase the chance of inappropriate routing, unexpected tool use, and user confusion, especially when the skill performs searches and generates booking-oriented output.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are common, everyday travel requests and do not clearly distinguish this skill from general travel assistants. This can lead to accidental invocation on unrelated or broader trip-planning queries, causing the system to prioritize a random-deals workflow when the user may need precise planning or neutral advice instead.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill content is written to operate in Chinese without offering language negotiation, which can override user preference and reduce transparency about what the skill is doing. While not a direct code-execution risk, forced language behavior can impair informed consent, increase misunderstanding, and make misuse or incorrect outputs harder for some users to detect.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal