ClawHub
Back to skill

Security audit

miniprogram-architect

Security checks across malware telemetry and agentic risk

Overview

This is a guidance-only WeChat Mini Program architecture skill with one rigid naming-style rule but no executable code or hidden system access.

Safe to install as an architecture guidance skill. Treat the Chinese-naming rule as a project style preference rather than a universal requirement, and review any generated Mini Program config, API wrapper, token-handling, and privacy-compliance code before production use.

SkillSpector

By NVIDIA
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
Confidence
88% confidence
Finding
The skill imposes a hard rule that Chinese naming is not allowed, without any user opt-in or project-specific justification. This can override user preferences, team conventions, or localization needs, and may cause the agent to reject valid requests or steer output in an unnecessarily restrictive way.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.