中文去AI味
Security checks across malware telemetry and agentic risk
Overview
This is a simple Chinese writing-style skill that rewrites AI-sounding text to feel more natural and does not request code execution, credentials, network access, or persistence.
Install it if you want help making Chinese text sound less mechanical. Use it carefully in contexts where authorship or AI disclosure matters, and avoid inventing personal experiences or presenting AI-assisted text as a real person's lived account when that would mislead readers.
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
65/65 vendors flagged this skill as clean.