ClawHub
Back to skill

Security audit

Amap Smart Route

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Amap route-planning helper that discloses its external API use and required API key.

Install only if you are comfortable providing an Amap API key and sending route origins/destinations to Amap. For ambiguous travel requests, confirm the exact origin, destination, and travel mode before allowing the skill to call the API.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

L003 的显示名称及全文说明均固定为中文，且未说明是否支持用户以其他语言交互或允许语言选择。按照该规则，若技能对语言/locale 做出单一限定而未提供用户选择或明确合理依据，属于自然语言策略风险。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises broad trigger phrases such as asking how to get from A to B, how long a trip takes, or to help plan a route. In an agent environment, overly generic travel-related language can cause the skill to activate in situations the user did not explicitly intend, leading to unintended external API calls and disclosure of user-supplied locations to a third party.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.