Back to skill

Security audit

Agent Self Assessment Publish

Security checks across malware telemetry and agentic risk

Overview

This markdown-only skill is a disclosed, tool-free self-assessment prompt with optional AGIRAILS install references that are not executed by the skill.

Safe to install as a prompt-based checklist. Treat its compliance output as advisory, not legal certification, and only run the optional AGIRAILS package-install commands if you independently want that transaction infrastructure and have reviewed those dependencies.

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

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.