ClawHub
Back to skill

Security audit

de-ai-ify

Security checks across malware telemetry and agentic risk

Overview

This is a text-rewriting skill that only guides an agent to detect and reduce AI-like writing style, with no code, persistence, credentials, or external access.

Before installing, note that the skill may activate on some general Chinese polishing or rewrite requests. Use explicit wording when you want only proofreading, translation, or technical editing rather than AI-style reduction.

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
88% confidence
Finding
The trigger list includes broad, common editing requests such as “润色”, “改稿”, and “改得更自然”, which can overlap with many unrelated writing tasks. That can cause the skill to activate outside its intended scope, leading to unwanted content transformation or interference with other more appropriate skills, especially when user intent is ambiguous.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.