ClawHub
Back to skill

Security audit

TradingBot

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local installer and runner for TradingBot, with meaningful cautions around demo mode, secrets, and user confirmation.

Install only if you trust the upstream TradingBot repository and are comfortable building third-party code locally. Keep the first run in demo/mock mode, do not enter live exchange credentials unless you intentionally accept trading risk, and do not expose the local port to the public internet.

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
90% confidence
Finding
The skill clearly instructs the agent to execute shell commands for cloning, building, and running third-party code, yet no explicit permissions are declared. This creates a privilege/transparency gap: users and enforcement layers may not realize the skill can perform impactful local system actions, including downloading and executing untrusted code from GitHub.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.