ClawHub
Back to skill

Security audit

国创赛商业模式设计

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only coaching skill for 国创赛 business-model preparation, with no code execution or hidden data access found.

Use this skill for 国创赛 business-model drafts, PPT sections, and answer-prep. Be careful when sharing unreleased project details, contracts, private financials, or proprietary IP, and verify current competition rules and market data before submitting generated materials.

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
94% confidence
Finding
The trigger list is very broad and contains common business terms such as 商业模式, 市场定位, 竞品分析, and 财务预测 that can appear in ordinary conversations outside the intended contest-preparation context. This can cause unintended invocation of the skill, leading the agent to apply competition-specific guidance in irrelevant contexts, increasing prompt-routing errors and reducing response safety and reliability.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal