Stocks and Financial Data Pull Crypto Finance Cryptocurrency Price Earnings Dividends

• Outcome: Pass
• Latest audit: May 28, 2026, 1:24 PM
• Version:
  4.2.1

Overview

This is a disclosed Yahoo Finance lookup skill with some routing, dependency, and bulk-query hygiene issues, but no evidence of trading, credential theft, destructive behavior, or hidden persistence.

Install only if you want an agent to make Yahoo Finance-backed market-data requests. Use it in an isolated virtual environment, consider pinning dependencies for repeatable installs, narrow the routing rules to explicit finance questions, and avoid running self-test or complete analysis unless you expect many outbound requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill explicitly instructs the agent to install dependencies and invoke Python code that calls Yahoo Finance-backed tooling, which implies network access, yet no permissions are declared. This creates a transparency and policy-enforcement gap: an agent or platform may treat the skill as lower risk than it is and allow outbound requests without informed consent or proper sandboxing.

Vague Triggers

Medium

• Confidence: 78% confidence
• Finding: The routing guidance includes a vague trigger such as 'Tell me about', which is broad enough to match ordinary conversation and could cause this skill to be invoked when the user did not clearly request financial data. In an agent environment, overly broad auto-routing increases the chance of unintended tool use, unnecessary network calls, and disclosure of user prompts to external services.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The built-in self-test fans out into dozens of outbound Yahoo Finance requests and related lookups in one call, which can be triggered by a simple natural-language prompt. In an agent environment, this creates a denial-of-wallet/denial-of-service style risk through excessive network activity, rate-limit exhaustion, noisy external access patterns, and accidental use against untrusted or high-volume workflows.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The complete-analysis routine automatically chains a very large set of data-fetching functions, including peer comparisons and market context calls, causing broad outbound access from a single invocation. In agent contexts this is risky because a prompt can trigger heavy unsolicited network activity, amplify rate limiting, leak usage patterns to third parties, and consume resources far beyond what a user may expect.

VirusTotal

66/66 vendors flagged this skill as clean.