惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Martin Fowler
Martin Fowler
V
Visual Studio Blog
有赞技术团队
有赞技术团队
T
Tailwind CSS Blog
B
Blog
I
InfoQ
博客园 - 三生石上(FineUI控件)
阮一峰的网络日志
阮一峰的网络日志
F
Fortinet All Blogs
H
Help Net Security
博客园 - Franky
宝玉的分享
宝玉的分享
博客园 - 司徒正美
C
Check Point Blog
G
Google Developers Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Jina AI
Jina AI
T
The Blog of Author Tim Ferriss
MongoDB | Blog
MongoDB | Blog
云风的 BLOG
云风的 BLOG
A
About on SuperTechFans
罗磊的独立博客
大猫的无限游戏
大猫的无限游戏
IT之家
IT之家

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Token-2022 Traps That Drain AI Trading Agents (and How to...
MrWizardlyLoaf · 2026-06-23 · via DEV Community

MrWizardlyLoaf

Most "rug pull" content on Solana is about classic SPL tokens — mint authority, liquidity pulls, whale dumps. But the sharper edge now is Token-2022: a newer token standard whose extensions give a creator powers a normal SPL token never had. For an autonomous trading agent that buys tokens by address, these are landmines.

Here are the extensions that actually drain agents, and how to screen for them before a buy.

The dangerous extensions

  • permanentDelegate — the single worst one. The creator holds a permanent delegate that can move or burn your tokens out of your wallet, any time, with no further approval. You hold the token; they hold the keys to it.
  • transferHook — a custom program runs on every transfer and can make selling fail under conditions the creator chooses.
  • pausable — transfers (including your sell) can be paused at will.
  • nonTransferable — the token literally cannot be moved once you hold it. Permanent honeypot.
  • defaultAccountState = frozen — new holder accounts start frozen; the issuer decides who can transact.

None of these are visible on a chart or a typical token page. They live in the mint account, and they are readable on-chain — if your agent reads them before trading.

Screen for them in one call

RugCheck AI reads the mint directly (getAccountInfo) and flags these extensions explicitly:

check_authorities("<mint>") -> mint/freeze authority + every Token-2022 extension, with the dangerous ones called out

scan_token("<mint>") -> { verdict: SAFE|CAUTION|DANGER, safety_score, risks: [...] }

A token carrying permanentDelegate or a transfer hook comes back DANGER with the reason spelled out, before your agent spends anything.

Why "read the chain directly" matters

Indexers and token lists often don't surface Token-2022 extension data, and they definitely don't have it for a token minted a minute ago. RugCheck AI calls getAccountInfo on the mint itself, parses the extensions, and gives a real verdict on a fresh launch instead of unknown. The screening tools are read-only and never touch your keys.

Wire it in

Standard Streamable HTTP MCP server, no install, no API key. Add an mcpServers entry named rugcheck-ai pointing at the endpoint in Cline, Claude Desktop (via npx mcp-remote), or Cursor.

Endpoint:

https://web-production-58d585.up.railway.app/mcp

Rule for your agent: on DANGER, skip the token. Repo and full 15-tool list: github.com/MrWizardlyLoaf/rugcheck-ai (official MCP Registry: io.github.MrWizardlyLoaf/rugcheck-ai).