A Share Overnight Trading

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:33 PM UTC
• Version:
  1.0.0

Overview

This is a disclosed A-share overnight-trading guide with helper scripts; it carries financial-risk caveats but shows no hidden access, credential use, trading automation, or destructive behavior.

Install only if you understand this is educational trading material, not personalized financial advice. Treat the mock backtests and case studies as examples, not proof of profitability, and use real market data plus independent review before making any trade.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The script is positioned within a skill meant to support daily overnight stock selection, but the implementation only generates random synthetic market data and performs an offline mock backtest. In a financial-trading context, this mismatch is dangerous because users may mistake simulated outputs for actionable analysis, leading to poor investment decisions based on fabricated evidence.

Intent-Code Divergence

Medium

• Confidence: 95% confidence
• Finding: The file header and reporting language describe the output as a backtest and strategy evaluation, even though the data is randomly generated rather than derived from real market history. In this trading skill context, that framing materially increases the risk of deceptive or over-trusted results, since users may infer historical validation where none exists.

Intent-Code Divergence

Medium

• Confidence: 94% confidence
• Finding: The file presents itself as a backtest and prints analytical conclusions, but it only generates random synthetic data and then derives seemingly authoritative trading commentary from that fabricated output. In a trading skill, this is dangerous because users or downstream agents may treat the results as evidence-based strategy validation, leading to misinformed financial decisions despite there being no real historical testing.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The document provides concrete trading workflows, selection criteria, execution timing, and profit examples that could encourage real financial activity, while lacking a clear up-front risk disclosure and non-guarantee statement. In the context of a skill explicitly intended to help choose stocks for overnight trading, this omission increases the chance that users treat the material as dependable financial advice and underestimate losses from volatility, liquidity, or black-swan events.

VirusTotal

65/65 vendors flagged this skill as clean.