Back to skill

Security audit

Learned Workflows

Security checks across malware telemetry and agentic risk

Overview

This skill is a small note-only workflow reminder with no executable code, install hooks, credential use, or hidden data behavior found.

This appears reasonable to install as a lightweight workflow-memory skill. Review the stored workflow note first because it may bias future agent behavior toward that recorded preference, but I found no evidence of hidden execution, credential access, exfiltration, or destructive behavior.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.