ClawHub
Back to skill

Security audit

店雷达选品技能

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed guide for using a specific 1688 product-selection MCP connector, with the main caution that it can spend connector points when used.

Install this if you specifically want an assistant to use the 店雷达 dld MCP service for 1688 product research. Be aware that the skill tells the assistant to use that connector by default for 1688 selection tasks, and each connector call, including the initial availability/account check, may consume 1 point.

SkillSpector

By NVIDIA
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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger conditions are broad enough to activate this skill for nearly any request mentioning 1688, including generic product discovery or seller evaluation. Because the skill then mandates use of a specific external MCP connector and workflow, it can steer the agent into unnecessary third-party tool usage, data disclosure, and point-consuming calls even when the user did not explicitly ask for that service.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.