ClawHub
Back to skill

Security audit

Novel Writer

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese web-novel writing helper that stores novel drafts and metadata in a clearly bounded workspace folder.

Install this if you want a Chinese web-fiction drafting workflow that creates and maintains files under your workspace's novels folder. Before using it, make sure you are comfortable with it writing chapter drafts, outlines, character notes, and state.json metadata in that folder, and specify your preferred language if you do not want Chinese output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill’s activation description is very broad and can match generic writing or editing requests, causing the agent to invoke this skill in situations beyond narrowly scoped novel-writing workflows. Over-broad routing increases the chance that users are steered into a file-writing skill unexpectedly, which can lead to unintended workspace reads/writes or interference with other more appropriate skills.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The description is written to operate in Chinese by default without stating that language should follow the user’s preference. This can override user intent, reduce transparency, and in multilingual environments cause the agent to respond in an unexpected language, increasing the risk of misunderstanding instructions around file operations or content generation.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.