ClawHub
Back to skill

Security audit

小鹿选房

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed real-estate search skill that runs a named CLI and stores its own API key/config, with no artifact-backed evidence of hidden or malicious behavior.

Install this only if you are comfortable running the xiaolu-house npm CLI and giving it an API key for the housing service. Review the source/package if you do not already trust the publisher, and confirm before setting or clearing local config.

SkillSpector

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger guidance uses very broad phrases like '帮我找房' and '我要买房', which can cause the skill to activate from ordinary conversation without sufficiently confirming the user's exact intent. In a command-executing skill, overbroad activation increases the chance of unsolicited tool use, data queries, or workflow steering before the user has clearly consented to this specific housing service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to execute all 'npx -y xiaolu-house' commands on the user's behalf, including state-changing configuration operations such as setting an API key, changing the default city, and clearing config. This is dangerous because it authorizes local system changes and package execution without an explicit safety gate, warning, or per-action confirmation, creating risk of unintended configuration changes, secret handling issues, and execution of remote package code via npx.

Static analysis

No suspicious patterns detected.