Zhang Lei Perspective

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Zhang Lei-inspired business and investing perspective skill, with no code execution or data access, though its broad triggers and license mismatch deserve attention.

Install this only if you want business or investing discussions filtered through a Zhang Lei-inspired long-term value lens. Be aware it may activate on generic phrases about moats or long-term thinking, and verify the license with the publisher before reuse or redistribution.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrases are broad enough to activate on generic investing or business questions such as moat, long-term thinking, or value investing, which can cause the persona to engage when the user did not explicitly request it. This is dangerous because it can override user intent, steer answers into a branded perspective, and increase the chance of unsuitable financial-style guidance being delivered under an authority persona.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill forces a fixed persona/style and disclaimer format once activated, without considering the user's preferred language, tone, or whether they want role-based framing. This is risky because it can degrade transparency and user control, especially if activation was accidental, though it does not by itself create code-execution or data-exfiltration risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal