ClawHub
Back to skill

Security audit

AI智能交易Agent

Security checks across malware telemetry and agentic risk

Overview

This is a text-only trading-analysis prompt skill with broad finance triggers but no hidden execution, credential use, persistence, or trading authority.

Install only if you want an agent to help draft trading analyses and signal-style outputs. Treat its entry, stop-loss, take-profit, and position-size suggestions as educational prompts, not professional financial advice or instructions to trade.

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 phrases are broad and include common finance terms such as market analysis, stock picking, risk management, and trading signals, which can cause the skill to activate in ordinary financial conversations outside its intended scope. In a trading-related skill, over-triggering is risky because it may insert speculative or quasi-advisory content into general user discussions, increasing the chance of unsafe financial guidance or policy-boundary violations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.