Back to skill

Security audit

tldr

Security checks across malware telemetry and agentic risk

Overview

This skill is a small helper that tells the agent to use the local tldr command for concise command examples, with no bundled code or hidden access.

Install only if you trust the tldr executable already present or installed on your machine. Use this for quick command examples, and check full man pages, --help, or official documentation before running commands that could delete, overwrite, publish, or otherwise change important data.

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