ClawHub
Back to skill

Security audit

NadFun Token Creation

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it advertises, but it can upload user content and trigger fund-spending blockchain transactions without a clear confirmation step.

Review before installing. Only use it if you are comfortable sending the chosen image, token metadata, links, wallet address, and token details to Nad.fun, and require your agent to ask before every upload and before any wallet transaction. Verify the network, contract addresses, fees, total spend, and optional initial-buy amount before signing.

SkillSpector

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

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to upload user-provided images and token metadata to a third-party API endpoint without explicitly warning the user that their content will be transmitted off-platform and stored by Nad.fun infrastructure. This creates a privacy and consent issue, especially because images, descriptions, and linked social URLs may contain sensitive or identifying information and the skill presents the flow as routine.

Missing User Warnings

High
Confidence
99% confidence
Finding
The skill directs use of a wallet from another skill and provides code to call BondingCurveRouter.create() with msg.value, including optional initial-buy funds, but does not clearly warn that this will submit an irreversible blockchain transaction and spend the user's funds. In an agent setting, that omission is dangerous because users may not understand that deployment fees and purchase amounts will be charged from their wallet and cannot be easily recovered if they proceed unintentionally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.