Security audit

百度地图地址·零售连锁拓店选址分析

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed retail site-selection helper that uses a named external API and does not install code, persist, or request hidden access.

Before installing, users should understand that relevant brand, address, and coordinate queries may be sent to the publisher's API, and they should provide a DDT_API_KEY only in a controlled environment. The skill appears scoped to read-only analysis and includes clear limits around unsupported data and credential handling.

SkillSpector

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:33