ClawHub
Back to skill

Security audit

Crypto Backtest

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward crypto backtesting tool that fetches public market data and optionally saves local JSON results.

Install dependencies in a virtual environment, verify the package sources, and choose output paths intentionally because existing files at those paths may be overwritten. Market-data requests will be sent to the selected exchange, and results are simulations rather than trading guarantees.

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
86% confidence
Finding
The skill documentation indicates it can export backtest results to JSON, which implies file-writing capability, but no permissions are declared. That mismatch is a real security issue because agents or users may invoke the skill without clear awareness that it writes to disk, increasing the risk of unintended file creation or overwriting in the execution environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.