Steve Jobs Skill

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Steve Jobs perspective roleplay skill with no code execution, credential use, data access, or persistence.

Install this only if you want a strong Steve Jobs-style roleplay mode. For formal, educational, or customer-facing use, keep clear that responses are simulated and consider requiring an explicit opt-in before switching into the persona.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrases are broad enough to match ordinary conversation such as asking to think from Steve Jobs' angle, which can activate the skill when the user may not intend a full persona switch. In this file, activation also changes response behavior significantly, so accidental triggering can override normal assistant behavior and increase the chance of misleading, abrasive, or unwanted responses.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The skill mandates direct first-person impersonation and forbids meta framing after initial activation, removing user choice about roleplay style and reducing transparency. In context, this is more concerning because the persona is instructed to be highly assertive and sometimes insulting, which can misrepresent simulated opinions as authoritative guidance and make it harder for users to understand they are interacting with a stylized imitation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal