43
total weekly downloads
2 packages
@eigenart/agentshield
Six-layer AI agent security for ElizaOS on Solana — prompt injection defense, transaction policies, anomaly detection, and on-chain audit trail. Part of the AgentShield platform (agentshield.pro).
@eigenart/agentshield-mcp
MCP server for AgentShield — detect prompt injection, jailbreak, and social-engineering attempts in any text before your agent processes it.