Sun Yuchen's stock selection model

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:16 PM UTC
• Version:
  1.0.0

Overview

This skill coherently generates stock and sector reports from public market/news data, with no evidence of hidden data theft, destructive behavior, or deceptive execution.

Install only if you are comfortable with local Node.js scripts making outbound requests to public market/news services. If you provide TAVILY_API_KEY, use a key intended for this tool. Treat outputs as informational market commentary, not investment advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill declares no explicit permissions, yet its documented workflow invokes Node.js scripts that use environment variables and perform network access to fetch market data, news, and external search results. This weakens transparency and security review because operators and users cannot accurately assess what capabilities the skill requires before activation.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The documented purpose centers on sector research reports, but the skill also describes AI-specific news brief generation and abnormal-movement monitoring with periodic polling. This scope expansion can cause users or platform reviewers to approve the skill under a narrower trust model than its actual behavior, especially because continuous monitoring and watchlist tracking materially change runtime behavior and data access patterns.

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The invocation examples are broad, natural-language finance queries without clear activation boundaries, which can cause the skill to trigger on loosely related user requests. In an agentic environment, ambiguous triggering can lead to unnecessary external requests, unintended script execution, or finance-oriented output when the user did not intend to invoke this skill.

VirusTotal

66/66 vendors flagged this skill as clean.