Training Report

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned, with the main caution being careful handling of personal details in generated reports.

Before installing, decide whether names, contact details, or identifiable feedback are truly needed. Prefer anonymized or aggregated inputs, confirm who will receive any report, and avoid including sensitive personal observations unless there is clear consent and a clear purpose.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly solicits named individual feedback, background, starting level, behavior, and contact details, and may place them into a report without any built-in privacy notice, minimization rule, or consent check. In common workplace settings, this can lead to unnecessary collection and disclosure of personal or performance-related information, especially when reports are shared with management or external clients.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal