stock-monitor-lite

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed stock-alert tool that fetches public market and news data and generates advisory alerts, with no hidden account access or destructive behavior found.

Before installing, review or replace the bundled watchlist and cost values, keep the config and alert channel private, install dependencies from trusted sources, and treat all generated stock suggestions as informational rather than professional financial advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
77% confidence
Finding
The skill advertises and documents executable behavior (`python3 stock_monitor.py`) plus scheduled monitoring, yet no explicit permissions are declared while static analysis detected file read and network capabilities. That creates an authorization and transparency gap: users and the platform cannot reliably evaluate what local files may be read or what remote endpoints may be contacted, which is especially relevant for a finance-oriented skill that may process holdings and market data.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding
The documented purpose is stock monitoring and alerting, but the analyzed behavior reportedly extends into news scraping, sentiment analysis, deep analysis generation, and investment-advice-style recommendations beyond the declared scope. This mismatch is dangerous because it hides material functionality from users, expands data collection and outbound network behavior, and may cause users to rely on opaque recommendation logic in a sensitive financial context.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The README instructs users to configure a recurring task that analyzes stocks and pushes results through a channel, but it does not clearly warn that the skill performs ongoing monitoring and outbound notifications. This can lead to users enabling persistent background activity and message delivery without fully understanding the frequency, scope, or destination of notifications.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal