ClawHub

全能订酒店国内版

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed hotel-search CLI skill that uses a RollingGo API key, with credential-handling and unpinned-package cautions but no hidden or destructive behavior found.

Install only if you trust the RollingGo service and CLI package. Use a dedicated RollingGo key where possible, prefer skill-scoped environment configuration over command-line --api-key examples, and consider pinning a known package version if reproducibility matters.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrase includes the standalone term "rollinggo", which is overly broad and can match ordinary mentions of the brand, CLI, or related discussion rather than a clear hotel-search intent. This can cause unintended skill invocation, leading to unnecessary tool execution or disclosure of hotel-search capabilities in contexts where the user did not actually request them.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation explicitly recommends supplying the API key via the `--api-key` command-line flag, which can expose the secret through shell history, process listings, logging, and agent execution traces. In an agent or hosted tool environment, command invocations are often recorded, making this more dangerous than on a private local shell.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The document explicitly recommends passing the API key via the `--api-key` command-line flag and even shows `--api-key YOUR_API_KEY` in examples. Command-line arguments are commonly exposed through shell history, process listings, job control logs, and some telemetry/debug tooling, so this can leak a live credential to other local users or to logs. In this skill context, the risk is somewhat elevated because the file is operational guidance for repeated CLI use, making copy-paste of unsafe patterns likely.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal