ClawHub
Back to skill

Security audit

Bou Wallet

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly describes a wallet and trading API, but it gives an agent direct instructions for payments, trades, leverage changes, transfers, and withdrawals without enough user-confirmation or scoping guidance.

Install only if you trust Bank of Universe and intend to let an agent operate this backend. Use a dedicated, limited agent key if available, start with read-only endpoints, verify the backend URL and every upstream pay-and-call destination, and require explicit approval before any payment, trade, cancel-all, leverage change, transfer, or withdrawal.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents high-impact trading, transfer, and withdrawal operations but does not require explicit user confirmation, risk acknowledgment, or any safety interlock before executing them. In an agent setting, this can enable unintended order placement, leverage changes, transfers, or withdrawals from natural-language prompts or ambiguous instructions, causing direct financial loss.

External Transmission

Medium
Category
Data Exfiltration
Content
-H "Authorization: Bearer $AGENT_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://api.example.com/search",
    "method": "POST",
    "body": {
      "query": "BTC"
Confidence
79% confidence
Finding
The pay-and-call feature allows the agent to send arbitrary upstream URLs and request bodies through the backend, effectively enabling external data transmission to user-chosen destinations. In context, this can be abused for SSRF-like behavior, unintended disclosure of prompt-derived or user data to third-party endpoints, and payment-backed requests to untrusted services.

Static analysis

No suspicious patterns detected.