Back to skill

Security audit

OpenClaw 资金费套利

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed MEXC trading bot, but it needs Review because it can place live leveraged trades with user credentials and lacks mandatory safety controls.

Install only if you are prepared for real automated trading risk. Use a restricted MEXC API key with no withdrawal permission, set explicit exposure caps before any live run, avoid overriding the API base URL, and test with the smallest possible balance or sandbox-like setup first.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/funding_arb_mexc.py:41
Finding

Authenticated MEXC requests can be redirected to an arbitrary network endpoint

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/funding_arb_mexc.py:53
Finding

Default leveraged trading configuration has no mandatory per-order or aggregate exposure cap

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill instructs use of environment variables, reading and writing a state file, and making live exchange network calls, but it declares no explicit tool scope or permission boundaries. In an agent setting, this increases the chance of overbroad tool access and unintended execution of credentialed trading or filesystem actions beyond what the user clearly authorized.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill directly tells the user to set exchange API credentials and run a live trading bot, but it provides no warning about financial risk, credential sensitivity, or the consequences of automated order placement. In practice, this can lead to accidental exposure of secrets, unauthorized or mistaken trades, and real monetary loss if an agent or user follows the instructions without adequate safeguards.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The display name, short description, and default prompt are all written in Chinese, which creates a language-specific experience with no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking context. This matches the policy category for language or locale constraints that are imposed without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The natural-language instructions and description are entirely in Chinese and do not offer the user a language or locale choice. Under the stated policy, forcing a specific language without user opt-in can be a policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file includes a dedicated Chinese-only instruction block labeled '中文说明' but does not indicate that language is optional or provide a user-selectable locale policy. Under the policy rule, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.