ClawHub
Back to skill

Security audit

DeepBook CLI. Watch, Make & Take the Sui Market

Security checks across malware telemetry and agentic risk

Overview

This is a coherent DeepBook trading skill, but it guides agents through private-key setup and live crypto fund-moving operations without strong confirmation boundaries.

Install only if you trust the deepbook-cli npm package and intend to let an agent assist with crypto trading. Use testnet or low-value accounts first, prefer stdin for secrets, inspect ~/.deepbook permissions and contents, and require explicit approval before any deposit, trade, withdrawal, margin, or config-changing command.

SkillSpector

By NVIDIA
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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly guides users through wallet/config setup, key handling, and live on-chain trading, but it does not prominently warn that these actions can change persistent global state in ~/.deepbook and move real funds irreversibly. In an agent setting, this omission increases the chance that a user or downstream automation will treat operational examples as low-risk inspection commands and accidentally authorize harmful financial actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documented commands for setting API keys and importing private keys show direct credential entry without a strong warning about secret exposure risks in shell history, terminal logs, agent transcripts, or persistent config files. In a tool skill intended for agent use, this is dangerous because credentials may be echoed, captured, or mishandled by automation, enabling account compromise and unauthorized trading.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The end-to-end workflow walks through manager creation, deposit, live buy execution, and withdrawal using real asset amounts, but it lacks a prominent warning that these are real fund-moving blockchain operations that may be irreversible and fee-incurring. In this context, step-by-step executable examples substantially increase the likelihood of accidental financial loss, especially if an agent follows them mechanically after only a dry-run.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.