Back to skill

Security audit

Agent Memory Framework

Security checks across malware telemetry and agentic risk

Overview

This is a transparent local memory framework, but it gives the agent broad persistent memory and behavior-changing file authority that users should review before installing.

Install only if you want local persistent memory. Treat MEMORY.md, memory/*.md, and archives as private; do not store secrets; restrict all memory reads to private sessions unless you explicitly approve sharing; and review any proposed edits to AGENTS.md, TOOLS.md, skills, or cron jobs before allowing 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

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.