Multi-Dimensional Trading System

• Outcome: Review
• Latest audit: May 29, 2026, 9:29 PM
• Version:
  1.0.1

Overview

The skill appears to be a trading-analysis prompt skill, but its broad activation language could route ordinary finance questions into specific trading recommendations.

Review this carefully before installing. It does not appear to execute trades or access accounts, but it may produce specific trading recommendations from broad finance prompts. Use it only if you want this named trading framework to activate, and treat outputs as educational analysis rather than financial advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger keywords include broad, common phrases such as "day trading," "support level," and "resistance level" that can appear in ordinary financial conversation. In a prompt-activated skill system, this can cause unintended activation, routing user requests into a high-risk trading workflow that may generate concrete entry/exit recommendations without the user explicitly opting in.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The natural-language examples show that ordinary conversational requests like asking for support levels or moving averages are enough to activate the full skill. Because this skill is designed to output concrete trading decisions and price levels, ambiguous triggering increases the chance of unsolicited financial recommendations, misrouting, or overreach beyond what the user intended.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The activation logic includes broad natural-language intents such as 'can I trade this', 'what's the current position', 'is it suitable to enter', and 'how should I operate' for a specific asset. These common phrases can cause unintended invocation in loosely related financial conversations, making the skill more likely to override a more appropriate default behavior and produce specific trading guidance when the user did not explicitly request this skill.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger condition uses a broad intent description such as asking about short-term trading, entry/exit points, or trend analysis for any asset, which can cause the skill to activate on many ordinary finance questions outside its intended scope. In a prompt-based skill, overbroad activation increases the chance of unintended instruction injection, misrouting, or the model producing high-risk trading guidance when the user did not explicitly request this framework.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The keyword list includes generic terms like day trading, Fibonacci, support level, and resistance level, which are common across many benign market-analysis requests. This makes accidental invocation likely and, given the skill's capability to produce concrete trading recommendations, expands exposure to inappropriate or misleading outputs even when the user's request was general rather than a request for this specific system.

VirusTotal

63/63 vendors flagged this skill as clean.