ClawHub
Back to skill

Security audit

Crypto Price Prediction

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it fetches BTC/ETH price predictions using external APIs and stores only a local timezone preference.

Before installing, be comfortable with the skill contacting myfastapi.zeabur.app and CoinGecko for BTC/ETH price data and saving your timezone locally under your home config directory. Treat the output as informational only, not financial advice.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation describes behavior that requires network access and local file persistence, yet no permissions are declared. This can prevent informed consent and accurate policy enforcement, especially since the skill stores timezone data locally and calls third-party APIs.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill claims to be a simple wrapper around an external prediction API, but the documented behavior also includes CoinGecko price fetching, local timezone prompting/storage, and derived output computation. This mismatch undermines user trust and can hide additional data flows or persistence that users did not knowingly approve.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill does not prominently warn users that it stores timezone information locally and sends requests to third-party services. Even if the stored data is low sensitivity, undisclosed persistence and outbound requests create privacy and transparency risks.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
skill.js:47