Models
Security checks across malware telemetry and agentic risk
Overview
This skill is a markdown-only guide for choosing AI models and does not ask to run code, access data, or change the user’s environment.
This appears safe to install as an informational model-selection reference. Treat pricing and model-quality claims as general guidance, since AI model costs and capabilities change frequently; verify current provider details before relying on them.
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.