ClawHub
Back to skill

Security audit

DEX代币数据入门

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only OKX DEX token data lookup helper; it has some sloppy scoping and capability wording, but no artifact-backed evidence of hidden, destructive, or exfiltrating behavior.

Before installing, treat this as a rough documentation-only helper rather than a complete tool: verify any OKX endpoint or script yourself, avoid entering private API credentials unless you trust the environment, and do not rely on its data as investment advice. The broad trigger wording should ideally be narrowed to OKX DEX token price, liquidity, contract lookup, and supported-chain data queries.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The skill documentation is internally inconsistent about its allowed operations: it claims the free version is query-only and does not support batch operations, yet later states the core execution supports create/query/export and shows broader retrieval examples. In an agent setting, ambiguous capability boundaries can cause unintended invocation paths, over-broad execution, or user deception about what the skill may do.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger keywords are extremely broad, including generic terms like API design, data analysis, automation, search, and machine learning, which are not narrowly tied to this crypto-token lookup skill. In an agent ecosystem, this can cause the skill to activate for unrelated user tasks, expanding its execution surface and increasing the chance of inappropriate tool use such as exec/read/write in irrelevant contexts.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The declared coverage scope is overly expansive and ambiguous, listing long fragments and generalized scenarios that exceed the skill's stated purpose of DEX token data lookup. Over-broad activation scope is dangerous because it can cause the agent to select this skill for loosely related finance, analytics, or automation tasks, leading to mis-execution and unintended use of enabled tools.

Static analysis

No suspicious patterns detected.