ClawHub

陈东升思维视角 v2.0

Security checks across malware telemetry and agentic risk

Overview

This is a text-only business persona skill that does not request system access, credentials, commands, or background behavior.

Install this only if you want a simulated Chen Dongsheng-style strategy lens. Treat the output as interpretation based on public information, not as statements from the real person or professional financial, legal, medical, or regulatory advice.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes broad natural-language phrases such as '用陈东升的视角' and related variants without clear scope, disambiguation rules, or activation boundaries. This can cause unintended persona activation in unrelated conversations, leading the assistant to adopt a role unexpectedly and potentially override user intent or reduce answer neutrality in sensitive business, finance, or strategy contexts.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The activation section states that saying phrases like '用陈东升的视角分析这个问题' will activate the skill, but it does not define when the skill should not activate, how long activation persists, or how conflicts with higher-priority user instructions are resolved. This ambiguity increases the risk of sticky or accidental persona behavior, especially in multi-turn chats where quoted text, analysis of prompts, or third-party content may contain the activation phrase.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal