LLM Inference Performance Estimator
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed calculator for LLM performance estimates and shows no hidden execution, credential access, persistence, or data exfiltration.
This is reasonable to install for LLM performance estimation. When using a config file, provide only the intended model config.json or paste relevant public model configuration rather than unrelated private files.
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.