ClawHub

S2 中国品牌个性量表演算模型

Security checks across malware telemetry and agentic risk

Overview

This is a China-market brand personality analysis prompt skill with language and scoping caveats, but no evidence of harmful behavior.

Install this if you want a specialized Chinese-market brand personality analysis framework. Before relying on results, clarify whether values are simulated or search-derived, provide competitors for context, and ask for your preferred language or market scope if Chinese-localized analysis is not what you want.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 README says to 'wake up this SKILL' and provide a brand name, but it does not define a precise trigger phrase, activation scope, or clear boundary for when the skill should engage. In agent environments, overly broad invocation language can cause accidental or context-inappropriate activation, making the skill easier to invoke unintentionally and increasing the chance of misuse or prompt-scope confusion.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill text directs the agent to operate in Chinese only ('你是...' and the protocol is entirely Chinese) without giving the user a language choice or opt-in. This can override user language preference, reduce transparency, and increase the risk of misunderstanding or unsafe downstream actions if a user cannot accurately review the output.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal