ClawHub
Back to skill

Security audit

rule-catalog

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Hookify rule catalog that can create project-local `.claude` rule files when the user asks it to install rules.

Install this only when you intentionally want Hookify rules added to a project. Review any `.claude/hookify.*.local.md` files before relying on them, and use bulk install commands only in the repository where you want persistent agent rules changed.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list includes broad generic terms like 'install', 'rules', and 'templates', which can cause the skill to activate in contexts unrelated to Hookify. Because this skill instructs writing rule files into `.claude/`, unintended invocation could lead an agent to modify a user's project when the user did not specifically request this skill.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The installation instructions say Claude will write a rule into `.claude/hookify.<rule>.local.md`, but there is no prominent warning that invoking the skill causes file creation inside the user's project. In an agent setting, omission of this side effect reduces informed consent and increases the chance of unintended repository changes.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
87% confidence
Finding
Using 'install' as a trigger risks conflicting with generic or built-in install commands, causing this skill to be selected when a user intends another installation action. Because this skill can direct file writes and project changes, trigger shadowing increases the likelihood of unintended modifications or misuse by an agent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.