Security audit

商铺选址分析工具

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it advertises: it sends address/location queries to AMap and writes local HTML map reports for store site analysis.

Install only if you are comfortable sending the addresses you analyze to AMap services. Treat generated HTML reports as potentially sensitive because they can contain addresses, coordinates, nearby businesses/facilities, and an AMap JS key; store them in a private directory or delete them after use if needed.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill description states that it geocodes addresses via external APIs and generates HTML files locally, but it does not warn that user-provided address data will be transmitted to a third party or that artifacts will be written to /tmp. In a location-analysis skill, addresses can be sensitive business or personal data, and undisclosed local HTML output may expose data to other local users or later processes if the files are left behind.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill sends user-provided addresses and derived geolocation data to the AMap API, which is a third-party service, without any visible consent, notice, or minimization controls in this file. While this is core functionality rather than overtly malicious behavior, it creates a privacy and data handling risk because sensitive location information may be disclosed externally without clear user awareness.

Static analysis

No suspicious patterns detected.