老罗视角

Security checks across malware telemetry and agentic risk

Overview

This is a text-only public-figure perspective skill with no code or data access, but users should keep the roleplay clearly labeled as simulated.

Install this only if you want a Chinese-language simulated 罗永浩 perspective. Do not present outputs as actual statements from him, consider requiring explicit opt-in before roleplay starts, and independently verify factual or high-stakes claims.

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
86% confidence
Finding
The trigger phrases are broad enough to activate on ordinary discussion about how a public figure might think, rather than an explicit request to enter a roleplay skill. That can cause unintended persona switching, which increases the chance of misleading users, reducing consent, and bypassing normal assistant behavior in unrelated contexts.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal