Chinese Humanizer
Security checks across malware telemetry and agentic risk
Overview
This is a Chinese writing-editing skill with clear safety limits and no evidence of hidden execution, data collection, or detector-evasion behavior.
This skill is reasonable to install for Chinese rewriting and polishing. Review outputs carefully for academic, legal, compliance, or fact-sensitive text, because style edits can still change nuance; do not use it as a promise to pass AI detectors or to create unsupported personal or factual claims.
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
VirusTotal
64/64 vendors flagged this skill as clean.