ClawHub
Back to skill

Security audit

高德地图 (Fangtian)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AMap lookup helper, but users should understand that location queries are sent to AMap and that the referenced executable is not included in the artifact.

Before installing, confirm where the `amap` executable comes from, set only the required AMap API key, and avoid submitting sensitive home, workplace, route, or IP-location queries unless you are comfortable sending them to AMap.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill sends user-supplied locations, addresses, coordinates, routes, and possibly IP-related queries to the external AMap service, but the description does not clearly disclose this data transfer. This creates a privacy and transparency issue because users may reveal sensitive travel patterns or location data without informed consent, and the skill returns raw third-party JSON that may contain more data than the user expects.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description states the skill should be used for requests 'in China,' and the document later says it only supports mainland China, but there is no user opt-in or explanation that this is a region-specific limitation for compliance or provider coverage. That creates a natural-language locale constraint that may conflict with the requirement not to force a specific locale without justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.