ClawHub
Back to skill

Security audit

writing-rules

Security checks across malware telemetry and agentic risk

Overview

This skill is a markdown guide for creating local Hookify guardrail rules, with no hidden code or automatic data access found.

Before installing, understand that this skill is meant to help create persistent local guardrail rules that may warn or block future commands or file edits. Review any generated .claude/hookify.*.local.md rule before enabling it, especially block rules, and narrow or disable rules that interfere with normal 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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes generic terms like 'rules', 'patterns', 'validation', and 'safety' that are common in normal developer conversations, which can cause this skill to activate outside its intended scope. Because the skill writes behavioral guardrails and blocking rules, unintended invocation could interfere with agent behavior, create or modify restrictive rule files, or divert the workflow in ways the user did not explicitly request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.