ClawHub
Back to skill

Security audit

Insight Writer

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-oriented writing guidance skill with no evidence of hidden execution, data access, persistence, or harmful behavior.

Install this if you want a Chinese-style analytical writing assistant that uses structured essays and aphoristic phrasing. Users who need neutral tone, narrow routing, or non-Chinese output should state those preferences clearly when using it.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is broad enough to trigger on many ordinary writing or analysis requests, which can cause inappropriate activation and override more suitable skills or default behavior. In an agent system, over-broad routing expands the skill’s influence surface and increases the chance that users are steered into a rigid, high-persuasion writing mode without explicitly requesting it.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill is defined entirely in Chinese and prescribes a Chinese-language stylistic output without offering user language choice, which can conflict with user intent and platform expectations. In multi-language agent environments, forced locale behavior can degrade reliability, cause silent policy mismatch, and make the skill activate in contexts where the user expected another language or neutral formatting.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal