Back to skill

Security audit

Basal Ganglia Memory

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation-only placeholder for future habit-memory behavior and shows no code, data access, commands, or persistence.

This version appears safe to install as a placeholder, but it does not provide functional memory behavior yet. Re-review future versions if they add actual habit storage, background automation, command execution, broad local indexing, or access to private agent history.

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

50/50 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.