ClawHub
Back to skill

Security audit

Stop Slop Zh

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese writing style guide with broad auto-use language, but it does not request system access, credentials, commands, networking, or persistence.

Install this if you want Chinese prose automatically checked for AI-like style. Be aware it may over-apply to technical, legal, academic, official, or bilingual writing, so override it when exact wording, formal conventions, or your original tone matter more than style polishing.

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

High
Confidence
95% confidence
Finding
The skill’s trigger scope is extremely broad, effectively applying to almost any Chinese writing task. That creates an overreach risk where the skill may be invoked by default in unrelated or sensitive contexts, overriding more specific user intent or causing unnecessary prompt transformation at scale.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The skill mandates Chinese-writing use without presenting language choice or an opt-in mechanism. This can force undesired behavior in multilingual workflows, interfere with user preferences, and cause the agent to apply the skill when the user did not request Chinese-specific rewriting.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.