Smart Model Routing for Z.AI
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed z.ai model-routing guide and does not install code, request credentials, or add hidden access.
Install this if you want your agent to choose cheaper or stronger z.ai/GLM models automatically. For security reviews, production changes, legal/medical/financial advice, or other sensitive work, explicitly request a stronger model or disable cost-first routing.
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.