ClawHub
Back to skill

Security audit

Sparkbtcbot

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent about its Bitcoin wallet purpose, but it should be reviewed carefully because it gives an AI agent ongoing control of real funds and includes examples that expose wallet recovery phrases.

Install only if you intentionally want an agent to control a Spark Bitcoin wallet. Use REGTEST or very small balances for direct mnemonic mode, avoid running setup examples in logged or shared environments, and prefer a proxy or other scoped service with spending limits, destination/domain allowlists, audit logs, and human approval for withdrawals and payments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (5)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation text includes the broad trigger 'or wants Bitcoin L2 capabilities for an agent,' which can cause the skill to activate outside narrowly scoped Spark-specific requests. Because this skill enables direct custody and autonomous payments, over-broad activation increases the chance that an unrelated request results in wallet initialization or payment-capable guidance being invoked unnecessarily.

Missing User Warnings

High
Confidence
99% confidence
Finding
The demo prints a newly generated wallet mnemonic directly to the console, which can expose the wallet's full recovery secret through terminal history, CI logs, process supervisors, screenshots, or shared log collectors. Anyone who obtains the mnemonic can fully take over the wallet and drain funds.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
description: Network to connect to (MAINNET or REGTEST)
      default: MAINNET
model-invocation: autonomous
model-invocation-reason: This skill enables agents to autonomously send and receive Bitcoin payments. Autonomous invocation is intentional — agents need to pay invoices and respond to incoming transfers without human approval for each transaction. Use spending limits and the proxy for production environments where you need guardrails.
homepage: https://sparkbot.yvrbtclabs.dev
---
Confidence
97% confidence
Finding
autonomously send

Credential Access

High
Category
Privilege Escalation
Content
if (mnemonic) {
    console.log("\n=== SAVE THIS MNEMONIC SECURELY ===");
    console.log(mnemonic);
    console.log("\n=== Add to .env ===");
    console.log(`SPARK_MNEMONIC=${mnemonic}`);
    console.log(`SPARK_NETWORK=${network}`);
  }
Confidence
95% confidence
Finding
.env

Unpinned Dependencies

Low
Category
Supply Chain
Content
"type": "module",
  "description": "Claude Code skill for setting up Spark Bitcoin L2 wallet capabilities for AI agents",
  "dependencies": {
    "@buildonspark/spark-sdk": "^0.5.8",
    "dotenv": "^16.4.7"
  },
  "scripts": {
Confidence
89% confidence
Finding
"@buildonspark/spark-sdk": "^0.5.8"

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal