Communitygithub.com

LLM 交易代理安全指南

针对拥有钱包或交易权限的自主交易代理的安全模式。涵盖提示注入、支出限额、发送前模拟、断路器、MEV 保护和密钥处理。适用于需要审查自主代理的限额、模拟或密钥处理的情况。

LLM 交易代理安全指南 是什么?

该技能为构建或审计拥有钱包或交易权限的自主交易代理提供了全面的安全指南。它强调多层防御,将提示注入视为潜在的财务攻击,要求强制执行硬性支出限额,在发送交易前进行模拟,并实现断路器以防止损失。此外,还涵盖钱包隔离、MEV 保护和截止日期管理,以确保安全交易。该指南支持在 Python 环境中与以太坊钱包交互,可在 Claude Code、Cursor 等 AI 编码助手中使用,以增强代理安全性。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/llm-trading-agent-security

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

LLM 交易代理安全

自主交易代理面临比普通 LLM 应用更严酷的威胁模型:一次注入或错误的工具路径可能直接导致资产损失。

适用场景

  • 构建一个签署和发送交易的 AI 代理
  • 审计交易机器人或链上执行助手
  • 为代理设计钱包密钥管理
  • 赋予 LLM 访问下单、兑换或财库操作的权限

工作原理

分层防御。没有单一的检查就足够了。将提示卫生、支出策略、模拟、执行限制和钱包隔离视为独立的控制措施。

示例

将提示注入视为财务攻击

import re

INJECTION_PATTERNS = [
    r'ignore (previous|all) instructions',
    r'new (task|directive|instruction)',
    r'system prompt',
    r'send .{0,50} to 0x[0-9a-fA-F]{40}',
    r'transfer .{0,50} to',
    r'approve .{0,50} for',
]

def sanitize_onchain_data(text: str) -> str:
    for pattern in INJECTION_PATTERNS:
        if re.search(pattern, text, re.IGNORECASE):
            raise ValueError(f"Potential prompt injection: {text[:100]}")
    return text

不要盲目地将代币名称、配对标签、webhook 或社交动态注入到可执行提示中。

硬性支出限额

from decimal import Decimal

MAX_SINGLE_TX_USD = Decimal("500")
MAX_DAILY_SPEND_USD = Decimal("2000")

class SpendLimitError(Exception):
    pass

class SpendLimitGuard:
    def check_and_record(self, usd_amount: Decimal) -> None:
        if usd_amount > MAX_SINGLE_TX_USD:
            raise SpendLimitError(f"Single tx ${usd_amount} exceeds max ${MAX_SINGLE_TX_USD}")

        daily = self._get_24h_spend()
        if daily + usd_amount > MAX_DAILY_SPEND_USD:
            raise SpendLimitError(f"Daily limit: ${daily} + ${usd_amount} > ${MAX_DAILY_SPEND_USD}")

        self._record_spend(usd_amount)

发送前模拟

class SlippageError(Exception):
    pass

async def safe_execute(self, tx: dict, expected_min_out: int | None = None) -> str:
    sim_result = await self.w3.eth.call(tx)

    if expected_min_out is None:
        raise ValueError("min_amount_out is required before send")

    actual_out = decode_uint256(sim_result)
    if actual_out < expected_min_out:
        raise SlippageError(f"Simulation: {actual_out} < {expected_min_out}")

    signed = self.account.sign_transaction(tx)
    return await self.w3.eth.send_raw_transaction(signed.raw_transaction)

断路器

class TradingCircuitBreaker:
    MAX_CONSECUTIVE_LOSSES = 3
    MAX_HOURLY_LOSS_PCT = 0.05

    def check(self, portfolio_value: float) -> None:
        if self.consecutive_losses >= self.MAX_CONSECUTIVE_LOSSES:
            self.halt("Too many consecutive losses")

        if self.hour_start_value <= 0:
            self.halt("Invalid hour_start_value")
            return

        hourly_pnl = (portfolio_value - self.hour_start_value) / self.hour_start_value
        if hourly_pnl < -self.MAX_HOURLY_LOSS_PCT:
            self.halt(f"Hourly PnL {hourly_pnl:.1%} below threshold")

钱包隔离

import os
from eth_account import Account

private_key = os.environ.get("TRADING_WALLET_PRIVATE_KEY")
if not private_key:
    raise EnvironmentError("TRADING_WALLET_PRIVATE_KEY not set")

account = Account.from_key(private_key)

使用只包含所需会话资金的专用热钱包。切勿将代理指向主财库钱包。

MEV 和截止日期保护

import time

PRIVATE_RPC = "https://rpc.flashbots.net"
MAX_SLIPPAGE_BPS = {"stable": 10, "volatile": 50}
deadline = int(time.time()) + 60

部署前检查清单

  • 外部数据在进入 LLM 上下文之前已清理
  • 支出限额独立于模型输出强制执行
  • 交易在发送前已模拟
  • min_amount_out 是必需的
  • 断路器在回撤或状态无效时停止运行
  • 密钥来自环境变量或密钥管理器,绝不在代码或日志中
  • 适当时使用私有内存池或受保护的路由
  • 根据策略设置滑点和截止日期
  • 所有代理决策都经过审计日志记录,而不仅仅是成功发送

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

相关技能