De AI Polish
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed Chinese writing-polish guide that may rewrite drafts and punctuation, but it contains no executable payload, hidden access, persistence, credential use, or network behavior.
Install this if you want Chinese drafts checked for AI-like phrasing before final output. Keep a copy or review changes when working with important, quoted, bilingual, legal, or punctuation-sensitive text because the skill may rewrite sentences and normalize punctuation.
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
VirusTotal findings are pending for this skill version.