Back to skill

Security audit

okx-cex-bot

Security checks for vulnerabilities and agentic risk

Overview

This skill is for legitimate OKX bot management, but it gives an agent live financial trading authority with leveraged and stop actions that can sell assets or close positions without a strong mandatory warning flow.

Install only if you intend to let the agent manage OKX trading bots. Prefer demo mode first, use limited API permissions and small sizes, and require the agent to restate live/demo mode, leverage, stopType, and whether assets or positions will be sold or closed before every create, amend, or stop action.

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
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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill enables creation and amendment of live leveraged trading bots, including contract grids and contract DCA, but does not require a prominent user-facing risk warning or explicit acknowledgment of liquidation and loss risk before execution. In an agent setting, this increases the chance of users triggering financially dangerous actions without understanding that leverage and live mode can rapidly realize substantial losses.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The grid stop workflow documents that default stop behavior can sell all spot assets or market-close contract positions, but it does not mandate an explicit warning to the user at execution time. Because this is a destructive operation with irreversible financial consequences, an agent could stop a bot using defaults that liquidate holdings or close positions without sufficiently informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The DCA stop section similarly permits destructive outcomes, including immediate token sale for spot DCA or closing open contract positions, without a prominent execution-time warning. In an automated assistant context, this omission raises the risk of unintended liquidation or asset disposal from an ambiguous stop request.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.