ClawHub
Back to skill

Security audit

NS Trains

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Dutch train lookup skill that uses an NS API key only to request train information from the NS API.

Install if you are comfortable sending your station, route, and optional commute locations to the NS API. Keep NS_SUBSCRIPTION_KEY out of committed files or chat logs, and prefer a runtime secret manager or environment injection.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The natural-language triggers are very broad and generic, such as asking about the next train or disruptions, which can overlap with ordinary user conversation. In an agent environment, this increases the chance of unintended skill activation, causing the agent to invoke external API-backed actions or consume secrets/context when the user did not explicitly intend to use this skill.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/ns-api.mjs:10