ClawHub
Back to skill

Security audit

Crypto Trading Bot

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent crypto trading bot guide, but it should be reviewed because it encourages live automated trading workflows without clear safety boundaries.

Review carefully before installing. This skill should be updated to default to simulation or testnet, require explicit confirmation for live trading, warn about real-money losses and irreversible transactions, and document safe API-key permissions, logging, limits, and shutdown controls.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill promotes automated trading, exchange API integration, arbitrage, and potentially flash-loan-enabled workflows without any visible warning about financial loss, liquidation, API-key misuse, irreversible transactions, rate limits, compliance obligations, or the risks of unattended execution. Because the skill is specifically designed to help automate real trading actions, the absence of risk disclosures and safety boundaries materially increases the chance of harmful or reckless deployment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description and body are written entirely in Traditional Chinese/Cantonese-style phrasing, with no indication that users may choose another language. This can violate language or locale policy when a skill implicitly enforces one language without offering opt-in or alternatives.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase effectively matches a very common user request ('整交易Bot'), which can cause the skill to activate in broad situations without clear user intent or safety gating. In a high-risk domain like automated crypto trading, overbroad invocation increases the chance that users are funneled into guidance for exchange/API-connected automation without appropriate warnings, scoping, or confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.