ClawHub

ETF模拟交易回测系统

Security checks across malware telemetry and agentic risk

Overview

This is a coherent ETF backtesting helper with expected market-data access and no evidence of real trading, credential theft, hidden persistence, or destructive behavior.

Install only if you want a learning-oriented ETF simulation and backtesting helper. Treat its outputs as educational, not investment advice; verify results independently, note that it contacts Eastmoney over HTTP for market data, and avoid adding cron jobs unless you intentionally want scheduled analyses.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding
The skill explicitly describes fetching real-time and historical market data and references a trading script with a `get_realtime_data()` function, which implies network access. If the platform relies on declared permissions for review or runtime isolation, omitting this capability creates a transparency and governance gap that can lead to unreviewed external communications or data exfiltration paths.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The description includes broad finance-related trigger terms such as ETF simulation trading, backtesting, and technical-indicator trading that can appear in ordinary investment discussions. This can cause the skill to activate outside the user's intent, leading to unexpected handling of financial queries and potentially surfacing strategy guidance in contexts where it was not explicitly requested.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The automatic trigger list is generic and lacks boundaries, with phrases like '回测分析' and '技术指标交易' broad enough to match many unrelated or exploratory finance conversations. In a finance/trading context, ambiguous invocation is more sensitive because unintended activation may cause the assistant to produce quasi-advisory trading analysis or initiate data retrieval without clear user consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal