ClawHub
Back to skill

Security audit

okx-dex

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed OKX DEX API helper that uses OKX credentials to fetch quotes and transaction payloads, with no evidence of hidden signing, broadcasting, exfiltration, or persistence.

Install only if you intend to let an agent use OKX API credentials for DEX quote and transaction-data requests. Keep OKX secrets out of chat, use least-privilege API credentials where possible, and independently verify chain ID, token addresses, spender/router, recipient wallet, amount, allowance, price impact, and slippage before signing any approval or swap in a wallet.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly requires shell execution and access to sensitive environment variables, but it declares no permissions. This creates a capability/permission mismatch that can cause users or platforms to underestimate the skill's access level and approve execution without understanding that API secrets will be consumed by local code.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The README explicitly promotes generating approve and swap transaction payloads but does not warn users that these transactions can grant token allowances or move funds if signed and submitted. In a blockchain skill, omission of signing-risk, allowance-risk, and verification guidance can lead users to approve maliciously crafted or misrouted transactions without understanding the consequences.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.generated_source_template_injection

User-controlled placeholder is embedded directly into generated source code.

Critical
Code
suspicious.generated_source_template_injection
Location
SKILL.md:47