AI 文本净化器（中文版）

Security checks across malware telemetry and agentic risk

Overview

This is a local Chinese text cleanup and rewriting skill that openly reduces AI-like wording, with no evidence of hidden data access or automatic execution.

Install only if you want a local Chinese text analysis and rewriting tool. Review rewritten text for accuracy, choose output paths carefully, and do not use it to hide AI authorship where disclosure, academic integrity, or compliance rules require transparency.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Ssd 2

Medium

Confidence: 96% confidence
Finding: The skill is explicitly designed to reduce AI-detection signals, remove chatbot artifacts, and make AI-generated text appear more human. That enables evasion of academic integrity checks, platform disclosure requirements, provenance controls, or fraud-detection workflows, making misuse substantially more likely even if the tool is presented as writing improvement.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal