Back to skill

Security audit

Wiz by TradingWizard

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently connects OpenClaw to TradingWizard market tools, with optional OAuth for private paper-trading features that are disclosed and bounded.

Install the public market tools if you want TradingWizard market data in OpenClaw. Only run the optional OAuth setup if you are comfortable connecting your TradingWizard account and allowing the MCP server to access private workspace data and supported paper-trading controls; the artifact says these are not real-money trades and require confirmation.

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

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SETUP.md (reported line 26)May include surrounding context.

openclaw mcp login tradingwizard

text

OpenClaw stores the resulting OAuth credentials. Available tools follow the connected Free, Pro, or Ultimate plan. Access tokens never appear in tool results.

## Verify in chat

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
## Safety boundaries

- Anonymous tools are read-only and cannot access private accounts.
- Do not request or expose API keys, access tokens, or OAuth codes in chat.
- Supported paper controls require OAuth, the right plan, and clear user confirmation.
- Never turn paper results into a promise of future returns.
- Never place or claim to place a real-money trade.