ClawHub
Back to skill

Security audit

Okx Dex Token Tool Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a DEX token-data lookup guide with some overbroad wording and an optional callback URL that users should treat carefully, but I found no hidden, destructive, or deceptive behavior.

Install only if you intend to use it for OKX/DEX token-data lookups. Avoid using callback_url unless you control and trust the endpoint, and review any script or command the agent proposes before running it because this artifact does not include the referenced Python script.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation scope is extremely broad and includes generic phrases such as data analysis, reporting, statistics, visualization, and automation workflows, which can cause the skill to be invoked for requests outside its intended DEX-token domain. In an agent environment with read/write/exec tools enabled, over-triggering increases the chance the agent applies this skill in inappropriate contexts, potentially causing unintended external API use, misleading outputs, or unnecessary command execution.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documented callback_url parameter implies sending results to an external endpoint, but the skill provides no explicit warning, trust boundary explanation, or validation guidance. In practice, users or upstream prompts may unknowingly cause token-query results, metadata, or future enriched outputs to be exfiltrated to attacker-controlled URLs, which is more concerning in a tool that also advertises automation workflow use.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.