雷军思维视角

Security checks across malware telemetry and agentic risk

Overview

This is a low-impact persona/thinking-framework skill whose main risk is that it may activate on broad product or business wording more often than intended.

Install this if you want business or product advice framed through a Lei Jun-style lens. Be aware it may activate on common product-strategy terms even when you did not explicitly ask for that persona, so use clear prompts when you want or do not want this perspective.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation keywords are broad business/product terms such as '趋势', '极致', '专注', and 'MVP', which are common in ordinary discussions and can cause the skill to trigger when the user did not request a Lei Jun persona. This creates scope-control risk: the assistant may unexpectedly adopt a specific viewpoint, bias advice, and override normal response behavior in unrelated contexts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal