Back to skill

Security audit

Harness

Security checks across malware telemetry and agentic risk

Overview

This skill is a workflow guide that adds planning, guardrails, and bounded recovery behavior, with no hidden executable code or data collection found.

Before installing, understand that this skill will steer agents into a structured workflow and may delegate planning or implementation to a code-workflow receiver. That is expected for its purpose; review any custom pipeline, guard, or recovery receivers you configure, since those external skills determine the actual execution behavior.

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

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.