Llm Trading Agent Security

This is a security pattern library for LLM agents that can actually spend money or sign transactions. It covers the defense-in-depth approach you need when a prompt injection could drain a wallet: input sanitization with regex blocklists, hard spend limits per transaction and per day, pre-send simulation with slippage checks, circuit breakers that halt on consecutive losses or drawdown thresholds, and wallet isolation so your agent never touches the main treasury. The examples are Python-heavy and Ethereum-focused but the patterns translate. If you're building anything where Claude has signing authority, this is the threat model checklist you should be working from.

skills.sh installs: 5.6K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill llm-trading-agent-security --agent claude-code

Installs into .claude/skills of the current project.

Files

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

SKILL.md on GitHub