Trading Signal Pro

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.0

Overview

This is an instruction-only trading skill with no malicious code found, but it advertises 24/7 automated financial execution and profit claims without clear safeguards or evidence.

Review carefully before installing. Do not provide exchange credentials, wallet access, funds, or trading permissions unless the publisher supplies clear documentation for data sources, API permissions, read-only versus trading access, trading limits, manual approval controls, shutdown controls, and evidence that profit claims are non-guaranteed and substantiated.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Description-Behavior Mismatch

Medium

• Confidence: 94% confidence
• Finding: The manifest and title present the skill as signal analysis, but the documentation explicitly advertises automated 24/7 execution and platform API integration, which materially expands it toward autonomous trading/bot behavior. That mismatch can mislead users, reviewers, and policy controls about what the skill actually does, increasing the risk of unauthorized trading activity or unsafe financial automation.

Context-Inappropriate Capability

Low

• Confidence: 89% confidence
• Finding: The revenue, payback, and profit-potential claims market the skill like an investment product rather than a neutral analysis tool. In a financial context, such claims can pressure users into trusting or deploying the skill based on promised returns, creating fraud, compliance, and user-harm risk if the claims are misleading or unsupported.

VirusTotal

66/66 vendors flagged this skill as clean.