Case Study Builder

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only case-study writing helper; its main risk is that users may choose to share sensitive client details while using it.

Before installing or using this skill, avoid pasting confidential client names, NDA-covered facts, personal data, or internal metrics unless you are authorized to use them in a case study. Prefer anonymized descriptors and review any generated copy before publishing.

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
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly prompts users to provide client identity, project problems, scope, outcomes, and memorable moments without first warning them not to share confidential, NDA-protected, or personal information. In practice, this can lead users to disclose sensitive commercial details, client names, internal metrics, or restricted project context into the agent workflow, creating confidentiality and data-handling risk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal