Ai Model Comparison
Security checks across malware telemetry and agentic risk
Overview
This skill is an informational AI model comparison guide and does not contain code, install scripts, credential access, or hidden actions.
Safe to install from an agentic-security perspective. Treat model prices, quotas, and recommendations as informational because provider pricing changes often, and use caution with the included external contact details for paid consulting.
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
65/65 vendors flagged this skill as clean.