ClawHub
Back to skill

Security audit

高德地图JSAPI免费版

Security checks across malware telemetry and agentic risk

Overview

This skill is a map-development helper whose file, command, and network references are mostly disclosed and aligned with generating AMap JSAPI examples.

Install this as a benign development aid, but use it only for AMap JSAPI work. Review any generated HTML before using real API keys, avoid providing callback URLs unless you explicitly need them, and keep keys restricted with AMap domain allowlists.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Context-Inappropriate Capability

Low
Confidence
88% confidence
Finding
The skill accepts a `callback_url` despite being documented primarily as a JSAPI development helper, creating an unnecessary pathway for outbound network interaction. In an agent environment with `exec`/`write` tools, this can enable unintended data transmission or SSRF-like behavior if the agent is induced to send results to attacker-controlled URLs.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger condition is overly broad ('API integration, interface docking, webhook configuration, system connection'), which increases the chance the skill activates for unrelated development tasks. In practice, broad activation can cause an agent with `exec` and `write` capabilities to apply this skill in contexts involving files, credentials, or network endpoints it was not meant to touch.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill declares `exec` and `write` tools and documents callback behavior, but does not clearly warn that it may generate/modify files or cause outbound network communication. This reduces transparency and can mislead users or calling systems about the operational effects of invoking the skill, increasing the risk of unintended code execution, file changes, or data egress.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.