ClawHub
Back to skill

Security audit

Design Gate

Security checks across malware telemetry and agentic risk

Overview

This skill is a small local design-checking library whose behavior matches its stated purpose and shows no evidence of hidden data access or unsafe execution.

Install only if you want a simple local checklist-style gate for design documents. Treat its pass/fail score as advisory rather than a security or architecture authority, especially for sensitive or complex designs.

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
77% confidence
Finding
The skill is described in broad, generic terms as a 'generic design gate checker' that validates designs before implementation, without clear constraints on when it should be invoked or what inputs are in scope. Overly broad activation language can cause an agent to apply the skill opportunistically to unrelated or sensitive user content, increasing the chance of unintended data exposure, overreach, or incorrect automated gating decisions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.