乔布斯.skill - Steve Jobs思维操作系统

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This is a text-only Steve Jobs perspective roleplay skill; its main risk is persona confusion, not access to your files, accounts, or system.

Install this only if you want a simulated Steve Jobs-style advisor. Treat its responses as roleplay based on public-source synthesis, not authentic statements from Steve Jobs or authoritative factual guidance, and ask it to exit the persona or answer in third person when clarity matters.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Intent-Code Divergence

Medium

• Confidence: 94% confidence
• Finding: The skill metadata frames this as a perspective-based advisor, but the body instructs the agent to respond directly as Steve Jobs and suppress meta framing after the first turn. That increases identity confusion risk, can mislead users about the provenance of advice, and may cause the model to ignore safety-oriented clarification behavior in favor of staying in character.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The invocation rules trigger on broad, common phrases like asking to think from Jobs' angle or to switch modes, which can cause unintended activation in ordinary conversation. This raises the chance of accidental persona takeover, unexpected behavior changes, and user confusion about why the assistant is responding in a constrained style.

VirusTotal

66/66 vendors flagged this skill as clean.