Wechat Quick Setup

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.0

Overview

This is a coherent WeChat mini-program starter generator, but its backend templates can create unsafe database, payment, upload, and messaging behavior if deployed unchanged.

Review this carefully before installing or using it for a real app. Treat the generated backend as starter code only: add server-side authentication and authorization, collection allowlists, ownership checks, input validation, payment amount/order validation, file upload limits, database permissions, and separate development/test/production environment IDs before deploying.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Context-Inappropriate Capability

Medium

• Confidence: 96% confidence
• Finding: The generated CRUD cloud function accepts action, collection, data, id, and where directly from the caller and performs unrestricted database operations with no authentication, authorization, or collection allowlisting. In a cloud-function context, deploying this template as-is can expose arbitrary reads, writes, updates, and deletes across backend data, making it a dangerous insecure-by-default scaffold.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The skill advertises generation of login, user-system, and cloud templates but provides no warning that these components will likely process sensitive identifiers such as OpenID, AppID, profile data, and potentially order or account data. In a quick-start scaffold, missing security guidance can lead users to deploy insecure defaults, over-collect user data, or mishandle authentication and authorization logic in production.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill instructs users to run cloud setup and database initialization commands against a specified environment without warning that these actions can create, modify, or initialize remote Tencent Cloud resources. This increases the risk of accidental changes to live environments, unintended charges, destructive initialization, or exposure caused by misconfigured backend resources.

VirusTotal

64/64 vendors flagged this skill as clean.