Llm Trading Agent Security

If you're building an AI agent that can actually send transactions or move money, this gives you a layered defense checklist. It covers prompt injection detection tuned for wallet addresses and transfer commands, hard spend caps with daily limits, mandatory pre-send simulation with slippage checks, circuit breakers that halt on drawdown, and wallet isolation patterns. The examples are Python but the ideas port anywhere. The core insight is right: no single control is enough when a bad LLM output can drain funds. Treat every piece of external data as hostile, simulate before you sign, and keep the agent's keys separate from your treasury.

skills.sh installs: 3.6K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/everything-claude-code --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