ClawHub
Back to skill

Security audit

Wang Wei Perspective V2

Security checks across malware telemetry and agentic risk

Overview

This is a text-only simulated business-persona skill; the main caveat is that broad trigger phrases could activate roleplay unexpectedly.

Install this only if you want a simulated Wang Wei/SF Express-style business perspective. Treat outputs as roleplay based on public information, not real-person advice, and use the stated exit phrases if it activates when you did not intend it.

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
89% confidence
Finding
The trigger list contains broad phrases such as logistics- and strategy-related terms that are not uniquely tied to this persona skill. This can cause unintended activation in normal conversations, leading the agent to enter a rigid roleplay mode unexpectedly and potentially override the user's actual intent or system behavior expectations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.