Plumber by trade. Open-source developer. Building Pipelock, Open-source AI agent firewall with mediator-signed action receipts.
pipelock. Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
786agent-egress-bench. Tool-neutral attack corpus for AI agent egress security
5pipelock-rules. Official community detection rules for Pipelock - the open-source agent firewall
3pipelock-verify-python. Python verifier for Pipelock action receipts (Ed25519-signed, chain-linked)
2pipelock-agent-egress-action. GitHub Action for running agent-driven CI jobs through Pipelock with verifiable egress evidence.
1