ClawHub
Back to skill

Security audit

architecture-aware-init

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent project-initialization guide that uses research and scaffolding instructions without hidden persistence or unrelated access.

Install this when you want architecture selection as part of new project setup. Invoke it deliberately, review generated scaffolds and ADRs before keeping them, and inspect the external Night Market plugin scripts separately before running the optional automation 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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list contains broad terms like "architecture," "initialization," and "research," which are common in ordinary developer conversation and could cause unintended activation of this skill outside clear user intent. Because the skill directs follow-on loading of additional modules and workflow steps, accidental invocation can steer agent behavior, consume resources, or override a more appropriate skill selection path.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.