Back to skill

Security audit

Core Refinery

Security checks across malware telemetry and agentic risk

Overview

Core Refinery is a markdown-only synthesis skill that asks the agent to summarize user-provided sources and does not request hidden execution or privileged access.

Installers should only provide source material they are comfortable processing with their configured model provider. Review synthesized outputs before sharing or treating them as canonical, because they may preserve confidential details or repeat mistakes from the inputs.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.