The latest articles on DEV Community by HamTek (@hamtek). https://dev.to/hamtek https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F3989747%2F2bd08b2f-ba85-4207-a8fb-532ed62350b1.png https://dev.to/hamtek en HamTek Wed, 17 Jun 2026 20:21:09 +0000 https://dev.to/hamtek/leakproof-stop-your-ai-coding-tool-from-leaking-secrets-to-the-cloud-local-apache-20-39fn https://dev.to/hamtek/leakproof-stop-your-ai-coding-tool-from-leaking-secrets-to-the-cloud-local-apache-20-39fn <p>Author here. The problem leakproof targets: AI coding tools (Claude Code, Cursor, aider) ship a lot of working-tree context upstream, and if any of it contains a secret — an .env value, a key in a fixture, a token in a comment — it can leave before you notice. That's a big reason compliance-bound teams end up banning these tools. leakproof is a local proxy between the tool and the model API: outbound requests get scanned and redacted before they leave the machine. Nothing calls home — no cloud account, the audit log stays local. There's also a git pre-commit gate. You can check it out at <a href="https://github.com/acunningham-ship-it/leakproof" rel="noopener noreferrer">https://github.com/acunningham-ship-it/leakproof</a> and I'll anwser any questions below.</p> ai webdev programming safety