Model Routing Orchestrator
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only model-routing skill with no evidence of code execution, credential access, persistence, or hidden behavior.
Install this if you want an agent to use cost-aware model-routing guidance. Because it can influence which model or workflow handles future requests, use it where that routing behavior is desired, but the reviewed artifacts do not show suspicious access, execution, 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
55/55 vendors flagged this skill as clean.