ClawHub
Back to skill

Security audit

WeChat Mini Program → uni-app + Vue3 + TypeScript Conversion

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward project converter that reads a WeChat Mini Program and writes a new uni-app/Vue/TypeScript project, with ordinary file-write caution.

Install this only when you want an agent to inspect a Mini Program source tree and create a converted uni-app project. Use a fresh output directory, avoid pointing it at an existing project unless you intend changes there, and review generated code and dependencies before running npm install or build commands.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger conditions are broad enough to activate on loosely related requests such as analysis or code generation around Mini Program projects, increasing the chance the skill runs in contexts where the user did not clearly authorize a full conversion workflow. In a file-writing skill, overbroad activation can cause unintended project creation or modification and reduce meaningful user consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs writing a complete converted project to disk without an explicit safety notice, dry-run option, or confirmation checkpoint before creating or overwriting files. In an agent setting, this can lead to unintended filesystem changes, data loss, or writes to attacker-influenced paths if the provided output directory is unsafe.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.