Security audit

腾讯地图地址·餐饮连锁拓店选址分析

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Chinese-language restaurant site-selection helper that uses a disclosed third-party API key and does not show hidden execution, persistence, or data-exfiltration behavior.

Before installing, confirm you are comfortable using GotoShop/DDT's API and sending restaurant names, locations, and address queries to that service. Keep the API key private and treat the generated market analysis as a data-snapshot aid, not as official Tencent Map or brand data.

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

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

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest fields and the full SKILL.md content require Chinese as the interaction language, but nowhere do they state that users may choose another language or that Chinese is a justified locale restriction. This can violate language/locale policy because it forces a specific language without user opt-in.
Content: No source excerpt is available for this finding.