ClawHub
Back to skill

Security audit

Crypto DRT Scalping

Security checks for vulnerabilities and agentic risk

Overview

This is a trading-plan skill with an optional paid signal client, but it needs Review because it can send a spending API key to a hard-coded remote service that charges per use.

Install only if you intentionally want this paid signal service. Verify the provider, wallet, pricing, and endpoint independently, use a tightly limited API key if available, expect charges when the signal script runs, and do not enable HTTP transport for a spending-capable key.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill metadata requests network access to a hard-coded external IP address and access to an environment variable containing an API key, yet the presented skill is primarily documentation for a trading strategy rather than a clearly permissioned integration. That combination creates a real risk of secret transmission and billable remote calls without sufficiently explicit permissioning or user-facing disclosure.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The skill is described as a crypto scalping/backtest strategy, but it also advertises live paid signal fetching that uses a spending-capable API key and remote network access to an external server. This mismatch is dangerous because users may invoke what appears to be an educational or analytical skill while unknowingly authorizing chargeable requests and exfiltrating credentials to a third party.

Context-Inappropriate Capability

Medium
Confidence
78% confidence
Finding
This script introduces a spending-capable external API client into a crypto scalping skill, which is mismatched to the stated skill purpose and expands the attack surface. Even if the code uses HTTPS, a pay-per-call mechanism can create unauthorized charges, dependency on an unvetted third-party service, and operational risk if the endpoint or surrounding workflow is abused.

Static analysis

No suspicious patterns detected.