SafeToken.fun

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  1.0.0

Overview

This skill is not malware-like, but it tells agents how to create real mainnet memecoins from a funded wallet without clear approval or safety controls.

Install only if you intentionally want agent assistance with SafeToken.fun token discovery or creation. Do not give an agent access to a primary wallet or private key; use a limited dedicated wallet, verify the chain ID, contract address, and ABI independently, simulate where possible, and manually approve every wallet transaction and public registration.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill instructs an agent to perform an on-chain token creation transaction and then register the token via API, but it does not warn that blockchain transactions are irreversible, incur gas costs, and may create lasting financial or reputational consequences. In an agent context, this omission increases the chance of autonomous or user-unaware execution of costly real-world actions.

VirusTotal

66/66 vendors flagged this skill as clean.