AGENT SKILL

llm-trading-agent-security

Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
llm-trading-agent-security
origin
ECC direct-port adaptation
version
1.0.0
description
Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.

03 SKILL.md 正文

LLM Trading Agent Security

Autonomous trading agents have a harsher threat model than normal LLM apps: an injection or bad tool path can turn directly into asset loss.

When to Use

  • Building an AI agent that signs and sends transactions
  • Auditing a trading bot or on-chain execution assistant
  • Designing wallet key management for an agent
  • Giving an LLM access to order placement, swaps, or treasury operations

How It Works

Layer the defenses. No single check is enough. Treat prompt hygiene, spend policy, simulation, execution limits, and wallet isolation as independent controls.

Examples

Treat prompt injection as a financial attack

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

Do not blindly inject token names, pair labels, webhooks, or social feeds into an execution-capable prompt.

Hard spend limits

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)

Simulate before sending

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)

Circuit breaker

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")

Wallet isolation

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)

Use a dedicated hot wallet with only the required session funds. Never point the agent at a primary treasury wallet.

MEV and deadline protection

import time

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

Pre-Deploy Checklist

  • External data is sanitized before entering the LLM context
  • Spend limits are enforced independently from model output
  • Transactions are simulated before send
  • min_amount_out is mandatory
  • Circuit breakers halt on drawdown or invalid state
  • Keys come from env or a secret manager, never code or logs
  • Private mempool or protected routing is used when appropriate
  • Slippage and deadlines are set per strategy
  • All agent decisions are audit-logged, not just successful sends

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1