ClawHub
Back to skill

Security audit

Anti AI-Slop

Security checks across malware telemetry and agentic risk

Overview

This is a text-only writing style skill that helps revise Chinese and English prose, with no evidence of hidden code, data access, or unsafe behavior.

Install this if you want a strong anti-formulaic writing editor for English and Chinese prose. Be aware that its style rules are opinionated and may over-edit tone, structure, adverbs, passive voice, and common phrases, so use it intentionally for writing cleanup rather than neutral editing.

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 description activates on very broad conditions such as drafting, editing, reviewing, or scoring text, which can match a large fraction of ordinary writing tasks. This can cause the skill to be invoked outside narrow user intent, leading to over-application of prescriptive rewriting rules and unintended interference with unrelated tasks.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.