ClawHub
Back to skill

Security audit

Shopee-爆款截流跟卖大师 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This Shopee analysis skill is a disclosed, purpose-aligned wrapper around Qinghu marketplace data APIs, with some user guidance needed around API keys, costs, and automatic exports.

Before installing, be comfortable giving this skill access to a Qinghu API key and allowing it to send Shopee and 1688 analysis requests to Qinghu. Tool calls may consume Qinghu credits after confirmation, and larger result sets may be exported to local table files automatically.

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 (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The metadata description says this skill 'must trigger' for a wide range of common Shopee requests, which creates over-broad activation scope. That can cause the agent to invoke this skill unnecessarily, leading to unintended external API use, needless credential prompts, and possible charges or data handling beyond user intent.

Vague Triggers

Low
Confidence
86% confidence
Finding
The '何时触发' examples are broad and illustrative but do not define hard boundaries for when the skill should or should not run. In context, this increases the chance of accidental invocation on generic Shopee discussions, which can steer users into external-tool workflows and paid operations they did not explicitly request.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill directs automatic file export whenever the result set reaches a threshold, even if the user did not request file creation. This can create local files and deliver links without informed consent, which is risky because file generation may expose sensitive marketplace data, surprise the user, or trigger downstream storage/sharing behavior they did not approve.

Static analysis

No suspicious patterns detected.