Security audit
Agentizer-zh — 镜像版 Humanizer-zh，AI 味精生成器
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed Chinese parody writing skill that changes response style, with no executable code, network behavior, credential use, or hidden data access.
Install this only if you want intentionally exaggerated Chinese AI-style rewriting. Prefer /agentizer for one-off rewrites, use /agentizer-on only when you want persistent style changes, and remember /agentizer-off restores normal replies.
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.
Static analysis
No suspicious patterns detected.