ClawHub
Back to skill

Security audit

architecture-review

Security checks across malware telemetry and agentic risk

Overview

This skill is a markdown-only architecture review checklist with broad but purpose-related triggers and no hidden execution, persistence, or credential handling.

Before installing, expect this skill to help an agent review architecture decisions and scan local project structure. Its broad triggers may cause it to appear during general design discussions, but the artifact does not add executable code, persistence, or hidden data access.

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
97% confidence
Finding
The manifest-style trigger list includes generic words like "architecture," "design," "patterns," and "principles," which are common in ordinary technical conversation and not specific enough to clearly distinguish when this skill should activate. The file does not provide trigger constraints, exclusion conditions, or negative examples to narrow activation scope.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.