Stock Price Checker Pro

• Outcome: Pass
• Latest audit: May 28, 2026 at 5:55 AM UTC
• Version:
  0.1.6

Overview

This stock checker runs a local Python script to fetch Yahoo Finance market data, and its sensitive behaviors are disclosed and proportionate to that purpose.

Install only if you are comfortable with a skill running local Python code, installing yfinance through uv, and contacting Yahoo Finance. For tighter supply-chain control, review or pin the yfinance dependency before first use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 80% confidence
• Finding: The skill instructs execution of local code and indicates capability to access environment data, but it declares no corresponding permissions or user-facing warning. This reduces transparency and can let the script read sensitive configuration or tokens from the runtime environment without the reviewer or user understanding that risk.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The skill is presented as a simple local stock-price checker, but its documented behavior expands to network-backed data retrieval, news collection, historical analysis, and corporate event fetching via Yahoo Finance. This mismatch is dangerous because users and agent policy may approve a narrow action while the skill performs broader external data access and processing than advertised.

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill description says it fetches current stock prices, but this function also retrieves and returns news, historical price ranges, market-cap/volume data, and corporate events. That scope expansion is a real security and trust issue because agents or users may invoke the skill expecting a narrow price lookup while it performs broader third-party data collection and output generation than advertised.

Context-Inappropriate Capability

Medium

• Confidence: 93% confidence
• Finding: Company-news retrieval is outside the stated purpose of a stock-price checker and introduces additional unneeded external content into the skill output. Pulling and presenting third-party news increases attack surface for prompt injection, misleading content, or privacy/compliance issues, especially in an agent context where untrusted text may later influence downstream behavior.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill directs the agent to execute a local Python script with `uv run`, which may auto-install dependencies and initiate network access, without clearly warning about code execution or package retrieval. This creates supply-chain and runtime risk because dependency resolution and script execution occur implicitly from a user request that appears to be a simple data lookup.

VirusTotal

65/65 vendors flagged this skill as clean.