Back to skill

Security audit

Agent Core

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable promotional stub that points to an unreviewed external automation kit advertised as having persistent memory and account-facing workflows.

Treat this listing as a preview or advertisement, not as a reviewed automation system. Before using the external kit, inspect every downloaded config, cron job, memory path, account integration, and safety rule; do not grant email, calendar, deployment, trading, or messaging access until you confirm scope, approvals, logging, disable controls, and cleanup steps.

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.