ClawHub
Back to skill

Security audit

Stock Market Pro

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed stock research tool with user-run Python commands and market-data network access, with no evidence of hidden persistence, credential theft, destructive behavior, or exfiltration.

Install only if you are comfortable running local Python tools and sending ticker/news queries to third-party market and search services. Use a virtual environment, review unpinned dependencies before installing, and skip the optional browser-based options-flow helper if you do not want browser automation or Unusual Whales access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly instructs the agent/user to execute local shell commands (`uv run`, `python3`, `pip3 install`) but does not declare corresponding permissions. This creates a trust and enforcement gap: an agent platform may treat the skill as low-privilege while the documented workflow still drives code execution, package installation, and browser-opening behavior on the host.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.