ClawHub
Back to skill

Security audit

Stock Tools

Security checks across malware telemetry and agentic risk

Overview

This is a user-run market quote script with documentation gaps, but it does not show credential theft, persistence, destructive behavior, or hidden data collection.

Install only if you are comfortable with ticker symbols being sent to Yahoo Finance, and crypto-style symbols being sent to Binance through a local proxy on port 7891. Review or change the proxy setting before running, and use a trusted Python environment for the requests dependency.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding
The skill declares no permissions in metadata, yet its documented behavior and referenced code require network access to fetch market data. This creates a transparency and governance gap: users and hosting platforms cannot accurately assess or constrain what the skill will do, which increases the risk of unexpected outbound connections and weakens trust boundaries.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The skill is ներկայացced as a Yahoo Finance-based US stock quote tool, but the analysis indicates additional behavior involving Binance, cryptocurrency price retrieval, and use of a local mihomo proxy. This mismatch is dangerous because it hides materially different network destinations and capabilities from users, making it easier to smuggle in undisclosed data flows, evade review, or route traffic through unexpected local services.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.