ClawHub
Back to skill

Security audit

Crypto Trading

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent but should be reviewed because it describes unattended crypto trading that can execute market orders and share account context with external AI services.

Install only if you intend to run an autonomous crypto trading workflow and have verified whether it uses paper or live trading, what exchange credentials it can access, what order limits and kill switches exist, and what account or portfolio data is sent to Dify AI and OpenClaw.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly describes an automated trading loop that executes live market orders every 10 minutes, but it does not warn users that it can place real trades autonomously. In this context, omission of that warning is dangerous because users may enable or invoke the skill without understanding that it can cause immediate financial loss through unattended execution, slippage, or erroneous AI-driven decisions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill states that it sends market analysis context and account holdings/balance data to external AI services (Dify AI and OpenClaw) without any privacy or data-handling warning. This is risky because portfolio positions, balances, and potentially strategy context may be disclosed to third-party providers, creating confidentiality, compliance, and data-retention exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.