ClawHub
Back to skill

Security audit

hotel-recommendation

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed hotel-search integration that uses a RollingGo API key and CLI, with some documentation issues users should handle carefully.

Before installing, confirm you trust the RollingGo CLI package source, store the API key in a scoped environment or secret configuration rather than passing it on the command line, and avoid entering unnecessary sensitive travel details. Be aware that hotel search parameters will be sent to RollingGo to obtain live results.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The manifest metadata declares the primary environment variable as `RollingGo_API_KEY`, while the pre-flight and key-check instructions later require `ROLLINGGO_API_KEY`. This is not merely incomplete documentation: following the declared metadata could leave the skill believing credentials are missing, directly contradicting the documented execution flow.

Vague Triggers

Medium
Confidence
92% confidence
Finding
该描述在触发短语列表中直接包含单独的“rollinggo”，没有限定必须是搜索酒店意图、命令格式或上下文条件。用户若只是提到品牌、官网或 API Key，也可能被错误判定为应调用本技能。

Missing User Warnings

Medium
Confidence
92% confidence
Finding
This markdown file includes an example using `--api-key YOUR_API_KEY`, which can expose secrets via shell history and process inspection on many systems. The surrounding documentation does not warn users about this risk or recommend the safer environment-variable method as the preferred approach.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
Natural-language policy violations include forcing a specific language without user opt-in. This file presents all instructions in Chinese and does not indicate that the skill is region-specific or provide an alternative language option.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This markdown file documents supplying an API key and invoking commands against a remote hotel service, which implies user queries and search parameters are sent over the network. The section explains how to configure credentials and call the service, but does not include any warning about external transmission, privacy implications, or handling of sensitive travel-related inputs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.