Security audit

AI Stock Master 股票大师

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed stock-analysis skill that sends market and ticker queries to TTfox, with no evidence of credential access, persistence, destructive actions, or hidden behavior.

Install only if you are comfortable sending market, sector, and stock-symbol queries to TTfox. Treat returned buy/sell-style recommendations as delayed research, not personalized investment advice, and watch for broad finance prompts that may invoke the skill.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill explicitly instructs the agent to fetch data from an external server ('TTfox.com') via functions such as get_market_sentiment() and get_stock_analysis(), but no permissions are declared in the manifest. Hidden or undeclared network access reduces transparency and weakens policy enforcement, especially for a finance-related skill that may transmit user queries or ticker interests to a third party.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The README documents very broad natural-language trigger examples such as "How is the market?" and "What are the hot sectors?" for automatic scenario activation. In an agent skill system, overly generic trigger phrases can cause unintentional invocation during ordinary conversation, which may lead to unwanted network access, financial-analysis actions, or confusing responses without clear user intent.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: Many trigger phrases such as 'Market Analysis', 'How is the market', 'Should I buy', and 'Stock Analysis' are broad enough to match normal conversation, causing the skill to activate unexpectedly. In this skill's context, accidental activation can lead to unsolicited external data fetches and finance-oriented responses in situations where the user did not intend to invoke the skill.

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The Chinese triggers include highly ambiguous everyday phrases like '分析股票', '大盘怎么样', and '市场行情', which can easily overlap with ordinary financial chat. Because the skill is wired to external quantitative functions, these broad triggers increase the chance of unintended activation and third-party data disclosure for Chinese-speaking users.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The method sends a user-supplied stock identifier to an external third-party service at master.ttfox.com, but this file provides no disclosure, consent flow, or privacy notice to the user. Even if a stock ticker is not highly sensitive by itself, it still reflects user intent and trading interest, and silent transmission to a remote service creates a data-sharing and privacy risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.