ClawHub

Liyou Setting Skill

Security checks across malware telemetry and agentic risk

Overview

This is a purpose-aligned writing and worldbuilding skill that persistently saves local creative content, with no evidence of hidden code, network access, credential use, or destructive behavior outside that purpose.

Install this only if you want the agent to save and update Liyou worldbuilding notes and novel chapters automatically. When you are only brainstorming or do not want something persisted, say so explicitly, and keep backups or version history for important drafts.

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)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly supports modifying, adding, deleting, and auto-saving worldbuilding and novel content, but it does not present any user-facing warning that these actions are persistent and data-changing. In an agent setting, this creates a meaningful risk of unintended edits or destructive changes being committed without the user's informed consent.

Missing User Warnings

High
Confidence
98% confidence
Finding
The rule tells the agent to directly call update functions and persist changes without asking the user first. This is dangerous because natural-language ambiguity, prompt injection through conversation content, or simple misunderstanding can cause irreversible edits to settings with no approval checkpoint.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to automatically save generated or discussed novel content to persistent storage whenever users discuss plot or request writing. This broad trigger can store drafts, speculative ideas, or sensitive content without clear user intent, leading to privacy, integrity, and unwanted-persistence issues.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal