ClawHub
Back to skill

Security audit

miniprogram-development

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent WeChat Mini Program development guide with disclosed tooling and cloud-operation guidance, not hidden or deceptive behavior.

Install this if you want agent help with WeChat Mini Program and CloudBase workflows. Before allowing preview, upload, publish, cloud database/function/storage changes, or MCP setup, confirm the project path, appid, cloud environment, and account login are the ones you intend to use.

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 (1)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The activation description is extremely broad and includes many generic software-development actions like create, modify, debug, test, deploy, review, and optimize. In an agentic system, this can cause the skill to be selected for requests outside narrow WeChat Mini Program scope, leading to misrouting, overreach into unrelated repositories or workflows, and inappropriate application of CloudBase- or deployment-specific guidance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.