Back to skill

Security audit

百度地图地址·零售连锁门店网络分析

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed retail-location analysis workflow using a specific external API and does not show hidden execution, persistence, or destructive behavior.

Before installing, users should understand that the skill sends retail brand names, addresses, coordinates, or public store IDs they provide to the DDT API, and they should keep the API key in a controlled environment variable rather than sharing it in prompts or files.

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:30