ClawHub
Back to skill

Security audit

Professional Novel Writing Techniques

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only novel-writing guidance skill with no code execution or sensitive access; its broad writing-related trigger wording is only a routing caveat.

Install this if you want general novel-writing technique assistance. Be aware it may activate for fairly broad writing, character, narrative, and literary-language requests; narrowing the trigger language would make routing cleaner, but the reviewed files do not show security-sensitive behavior.

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 invocation guidance is broad enough to activate on generic writing-related requests such as character development or writing improvement, which can cause the skill to be selected outside a narrowly intended scope. While this is not directly malicious and the skill content is harmless, overbroad triggering can lead to inappropriate routing, unnecessary prompt injection surface area, and interference with more suitable skills.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.