Find Skills 0

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent helper for finding and installing other skills, but users should review any third-party skill before approving a global install.

Install only when you explicitly want to add a new skill. Before running the suggested command, confirm the package name, source, and maintainer, and consider removing `-y` if you want the CLI confirmation step.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger guidance is broad enough to activate on very common user requests such as 'how do I do X' or 'can you do X,' which can cause this discovery/install skill to be invoked in situations where the user did not actually ask to search for third-party packages. In this context, that increases the chance the agent steers users toward installing external skills unnecessarily, expanding trust boundaries and creating supply-chain exposure.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill recommends `npx skills add <owner/repo@skill> -g -y`, which performs global, non-interactive installation of code from external sources without an explicit safety warning or confirmation step. In a skill specifically designed to discover and install third-party skills, this materially increases the risk of accidental or socially engineered installation of untrusted packages with persistent effects on the user environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal