Back to skill

Security audit

Truth Check

Security checks across malware telemetry and agentic risk

Overview

This skill is a small fact-checking prompt that asks the agent to verify claims and does not show hidden code, persistence, credential use, or destructive behavior.

Reasonable to install if you want a reminder workflow for checking factual accuracy. It may encourage the agent to verify external operations or look up sources, so review any resulting tool calls as usual, but the artifact itself does not request unusual access or privileges.

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

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.