ClawHub
Back to skill

Security audit

Orderly Ui Components

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent trading UI guide, but it includes real wallet connection and order-submission examples without clear safety boundaries for live trading.

Review this skill before installation if you plan to use its examples in a live trading app. Treat the order-entry and wallet snippets as capable of affecting real funds unless you explicitly configure a testnet or disabled-trading mode, and require user confirmation around any order placement or position-changing action.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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

Medium
Confidence
91% confidence
Finding
The skill documents wallet connection and live order submission flows without an explicit warning that these components may initiate real trading or interact with a user's wallet. In a trading context, omission of such warnings can cause downstream agent or developer misuse, increasing the risk of unintended financial actions and unsafe integration into automated flows.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The manifest frames the skill as providing pre-built React components for trading interfaces, which suggests UI composition guidance. However, the documented code invokes `onSubmit(params)` to actually submit trading orders, and other sections show active wallet connect/disconnect flows, which are transactional behaviors rather than merely building UI components.

Intent-Code Divergence

Low
Confidence
97% confidence
Finding
This section is documented as a Sheet/Drawer component example, but the inline UI intent implied by the `Close Position` button suggests an action that would close a trading position. In the code, the button has no handler and only renders text, so the presented intent contradicts the actual behavior.

Static analysis

No suspicious patterns detected.