Back to skill

Security audit

Social Automator

Security checks across malware telemetry and agentic risk

Overview

This skill is a small reference helper that prints static documentation and does not show evidence of accessing accounts, files, credentials, or networks.

This appears safe to install as a reference/documentation skill. Treat it as generic guidance rather than a real social automation tool, and do not provide credentials unless you independently add or run other tooling outside this skill.

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.