ClawHub
Back to skill

Security audit

Trip Planner Generator

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only travel-planning helper with visible language and routing limitations, but no hidden code or data access.

Install only if you want a guided itinerary-template workflow. Expect Chinese prompts and structured Chinese output unless you explicitly tell your agent to adapt language; provide only necessary trip details and use placeholders for sensitive identity or booking information.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill’s invocation criteria are very broad and overlap with ordinary travel-planning requests, increasing the chance the agent routes users into this skill when they did not explicitly ask for its workflow or output format. This can cause inappropriate tool selection, unnecessary data collection through multi-step questioning, and poor boundary control when other skills or direct answering would be more suitable.

Natural-Language Policy Violations

High
Confidence
97% confidence
Finding
The skill hard-codes Chinese-language questions and output formats without checking the user’s language preference, which can override user intent and degrade reliability of the interaction. In an agent setting, forced-language behavior can also propagate unusable downstream content to connected skills, causing workflow errors, misinterpretation of travel details, and poor user consent around how information is collected and presented.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.