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. Use when an autonomous agent holds wallet or transaction authority and its limits, simulation, or key handling need review.
- installs 8w
- 1,771
- 30-day movement
- starts with the next reading
- Related entries
- 5
- Connections
- 0
A SKILL.md agent skill that documents security patterns for autonomous trading agents holding wallet or transaction authority. It covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling, with sections for when to use, workflow, and examples.
Reach for it when an agent can sign and send transactions and its spend limits, simulation, or key handling need review.
Use it to
- Review spend limits and simulation before deploying a trading agent
- Audit an on-chain execution assistant's threat model
- Design wallet key management with isolation for an agent
- Run the pre-deploy checklist against an execution-capable agent
For Developers building or auditing transaction-signing AI agents
- Host repository
- affaan-m/ECC
- Version
- 1.0.0
- Installs, lifetime
- 3,100
- Installs, 8 weeks
- 1,771
- Host stars
- 261k
- Host language
- JavaScript