just for test

Security checks across malware telemetry and agentic risk

Overview

This is a minimal test placeholder skill with no code, install commands, permissions, or data access behavior.

This appears safe to install from a security perspective, but it is only a placeholder and likely will not add useful functionality. Confirm you intended to install a test skill rather than a production skill.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is too vague to define what the skill does, when it should activate, or what boundaries it should follow. Ambiguous descriptions can cause unintended invocation or misuse by downstream agents, increasing the chance of unsafe behavior or policy bypass through unclear scope.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal