Description
llm-trading-agent-security is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It sets out security patterns for autonomous trading agents that hold wallet or transaction authority, where a successful prompt injection or a bad tool call can directly cost assets. The skill layers several independent defences rather than relying on one check: prompt hygiene, spend policy, pre-send transaction simulation, execution limits, and isolation of the wallet keys. It treats prompt injection as a financial attack. It applies when building an agent that signs and sends transactions, auditing a trading bot or an on-chain execution assistant, designing wallet key management for an agent, or giving a language model access to order placement, swaps or treasury operations. The skill is a defensive reference for developers and does not itself trade. A skill is a SKILL.md file of instructions that an AI agent loads when a task calls for it. It is free and open source, and the skills.sh listing shows a Snyk warning, with Gen Agent Trust Hub and Socket passing.…
Highlights
- Layered defences, not a single check
- Spend limits and pre-send simulation
- Wallet key isolation
- Prompt injection treated as financial risk
Ratings & Reviews
No ratings yet
Be the first to rate llm-trading-agent-security.
People also visit
defi-amm-security
Security checklist for Solidity AMM contracts, liquidity pools, and swap flows
django-security
Django security best practices, authentication, authorization, CSRF protection
enterprise-agent-ops
Operational controls for long-lived or cloud-hosted agent systems
llm-trading-agent-security FAQ
What does the llm-trading-agent-security skill do?
It gives developers security patterns for AI agents that can sign and send transactions, so one injected prompt cannot drain funds.
What defences does it describe?
Prompt hygiene, spend policy, pre-send simulation, execution limits and wallet isolation, used together.
Does it trade?
No. It is a defensive reference for building and auditing agents.
How do I install it?
Run: npx skills add https://github.com/affaan-m/ecc --skill llm-trading-agent-security
Is it free?
Yes. It is free and open source.
Are there security warnings?
The skills.sh listing shows Snyk with a warning, while Gen Agent Trust Hub and Socket pass.
What are the best llm-trading-agent-security alternatives?
Popular alternatives to llm-trading-agent-security include healthcheck, defi-amm-security and django-security. See all llm-trading-agent-security alternatives