去 AI 味写作技能（中文）
Security checks across malware telemetry and agentic risk
Overview
This skill only provides Chinese writing-style guidance and does not include code, data access, or persistence.
This appears safe to install for users who want Chinese rewriting and tone-polishing guidance. Review the style preferences to ensure they match your desired voice, but the artifact does not show code execution, credential use, data collection, or persistence.
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.