Minimax Crypto Trading

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:44 PM UTC
• Version:
  11.0.0

Overview

This is an instruction-only crypto trading analysis skill with no code or credential access, but it can produce actionable trade parameters that users should treat cautiously.

Install only if you intentionally want crypto trading analysis. Do not connect it to exchange, wallet, or automation tools without separate review and explicit controls. Verify market data independently, size risk yourself, and prefer invoking the skill explicitly instead of letting broad crypto terms trigger it automatically.

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 (2)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger terms are broad, generic market-discussion words such as 'crypto', 'trading', and asset tickers, which can cause this skill to activate in ordinary informational conversations rather than only when a user explicitly wants trading actions. In this skill's context, that is risky because the agent is designed to output concrete trade/no-trade decisions and parameters, so accidental invocation can expose users to unrequested financial guidance.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill produces actionable trading outputs including direction, entry, stop loss, take-profit targets, and expected R, but it does not prominently warn users that these are financially consequential recommendations. In a financial-trading skill, the absence of a clear warning and limitation statement materially increases the chance that users will treat generated outputs as suitable-to-execute advice without understanding risk, uncertainty, or suitability concerns.

VirusTotal

64/64 vendors flagged this skill as clean.