Back to skill

Security audit

Verifiable-Recursive-Safety-Guardrails-Runtime

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for operating an external safety runtime, with no bundled executable code or hidden install behavior.

Safe to install as documentation. Treat any referenced AEGX Provenable runtime, daemon, installer, or binary as separate software: obtain it from a trusted source, verify integrity where possible, and understand its monitoring and persistence behavior before granting elevated access.

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

66/66 vendors flagged this skill as clean.

View on VirusTotal