Back to skill

Security audit

Skill Foundry

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed automation guide for finding public demand and optionally generating or publishing skill packages, with no bundled executable code or hidden behavior found.

Install with the understanding that the described workflow is meant to search public sources, generate many local skill files, and optionally publish to ClawHub or a GitHub repository if you provide the relevant CLI login or token. Review generated skills before publishing, and only provide GitHub tokens with the minimum repository access needed.

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