ClawHub
Back to skill

Security audit

code-quality-principles

Security checks across malware telemetry and agentic risk

Overview

This skill is a code-quality guidance document with no executable installation steps or hidden data access.

Before installing, be aware that the skill may activate on broad code-design or architecture discussions; its behavior is otherwise limited to general clean-code guidance and simple local review 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
93% confidence
Finding
The trigger list contains broad terms like `design`, `principles`, `architecture`, and `clean-code`, which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the attack surface for prompt injection and unintended tool or workflow influence, especially when the skill can introduce operational guidance such as shell commands.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.