Model Matrix
Security checks across malware telemetry and agentic risk
Overview
This skill is a read-only model-routing template with no code, install scripts, credentials, persistence, or hidden data access.
Before installing, understand that this skill can influence which model an agent chooses for different task categories, but it is documentation-only and does not add execution or data-access capabilities. Review future updates if they add code, network access, credentials, or automatic routing changes.
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
66/66 vendors flagged this skill as clean.
