ClawHub

Trading Strategies

Security checks across malware telemetry and agentic risk

Overview

This is a trading-strategy reference that contains risky financial guidance but no code, installs, credential access, persistence, or automatic trading behavior.

Install only as a trading education and strategy reference. Do not treat outputs as personalized financial, legal, or tax advice; verify any strategy independently, paper trade first, check platform and jurisdiction rules, and do not give an agent live trading keys or withdrawal permissions without a separate security review.

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
89% confidence
Finding
The front-matter description is broad enough to trigger this skill for many generic investing or trading-related requests without clear scoping. In a high-risk domain like finance, over-broad activation can cause the agent to provide quasi-advisory output or operational guidance in contexts where a narrower educational or analytical scope would be safer.

Vague Triggers

High
Confidence
96% confidence
Finding
The purpose statement explicitly says the skill should be used for 'making trading decisions,' which materially increases risk beyond a passive knowledge base. This can steer an agent toward actionable financial recommendations or decision support in a regulated, high-impact domain without qualification checks, user suitability checks, or risk controls.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal