ClawHub
Back to skill

Security audit

test

Security checks for vulnerabilities and agentic risk

Overview

This trading skill is coherent, but it can place real-money trades and run trading bots through chat without documenting clear confirmation gates or loss controls.

Before installing, confirm you intend to link VibeTrader and brokerage trading authority. Keep the API key protected, verify paper trading is the default, use broker-side limits or least-privilege permissions, and require explicit human confirmation before live orders, position closures, bot starts, or deletions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest explicitly advertises 'live trading' capability but provides no warning that the skill may place real-money trades or trigger irreversible financial actions. In an AI-agent context, this increases the risk that a user or upstream agent invokes trading features without informed consent, causing financial loss through mistaken, ambiguous, or overly broad natural-language instructions.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 3)May include surrounding context.

md
# VibeTrader Skill for OpenClaw

Create and manage AI-powered trading bots directly from WhatsApp, Telegram, Slack, Discord, or any other OpenClaw channel.

## Installation

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README explicitly encourages real-money trading actions such as "Buy $500 of TSLA" and promotes live trading, but it provides no warning about financial risk, order execution consequences, account linkage, or the possibility of unintended trades initiated through chat. In a multi-channel natural-language interface, ambiguous prompts, account compromise, or model mistakes can directly trigger costly real-world actions, making the omission materially dangerous.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: vibetrader
description: Create and manage AI-powered trading bots via natural language. Paper & live trading, portfolio monitoring, backtesting, stock quotes, and options chains.
homepage: https://vibetrader.markets
metadata: {"openclaw":{"homepage":"https://vibetrader.markets","category":"finance","requires":{"env":["VIBETRADER_API_KEY"]}}}
---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises high-risk and destructive financial actions such as live trading, manual order placement, position closing, bot creation, and bot deletion, but provides no explicit safety guardrails, confirmation requirements, or user-facing warnings about real-money loss and irreversible actions. In a finance skill, natural-language driven execution materially increases the chance of accidental harmful actions, especially when switching from paper to live trading is presented as a simple command.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.