ClawHub
Back to skill

Security audit

门店客流分析

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only store traffic analysis tool, but it depends on an unreviewed local API client and can fetch store business data with unclear credential scope.

Review before installing. Only use this skill in an environment where the external api_client is trusted and understood, and confirm which account credentials and store IDs it can access. Avoid running analyze.py directly unless the embedded sample store query is appropriate.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger conditions are very broad business phrases like asking how traffic is or requesting conversion analysis, which can easily overlap with ordinary conversation and cause the skill to activate unexpectedly. In this skill, unintended activation is more concerning because it is designed to pull store analytics data from an API, so a false trigger could cause unnecessary data access or disclosure in a context where the user did not explicitly request this tool.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly states that it pulls customerFunnel and behaviorFunnel data from an API, but it does not disclose network access behavior or warn that store analytics data will be transmitted and processed. Because this concerns potentially sensitive commercial performance metrics tied to specific stores and time ranges, hidden or implicit data transfer increases privacy, governance, and least-surprise risks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal