prose-enhancer专业文本润色助手
Security checks across malware telemetry and agentic risk
Overview
This is a Chinese prose-polishing skill that only works on text provided in chat and requests no external access.
Safe to install for Chinese writing refinement. Review outputs before using them in legal, medical, financial, marketing, or other fact-sensitive contexts because rewriting can change emphasis or introduce unsupported details.
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.