ClawHub
Back to skill

Security audit

瓦匠全流程助手

Security checks across malware telemetry and agentic risk

Overview

This is a masonry helper with disclosed local calculation and reference guidance, with no evidence of hidden data collection, persistence, or destructive behavior.

Install only if you want a masonry and tiling reference assistant. Treat its construction calculations and procedures as estimates, verify local building-code requirements, and consult a qualified professional for structural, waterproofing, electrical-adjacent, or safety-critical work.

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
89% confidence
Finding
The trigger list contains many short, common construction terms, which can cause the skill to activate on loosely related or incidental user messages. Unintended invocation can lead to irrelevant guidance, accidental disclosure of user context into the skill flow, or unsafe overreliance on generated construction advice in situations where the user did not explicitly request it.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The input-routing rules map broad natural-language phrases like '怎么做', '问题', or '标准' to specialized modules without robust disambiguation. This increases the chance that ordinary conversation is interpreted as construction advice, potentially producing unsafe procedural instructions or misleading calculations without sufficient context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.