LeakGuard

Local-only prompt protection for secrets and sensitive network data before they reach AI chat sites.

LeakGuard helps reduce accidental data leaks when working with AI chat tools. It runs locally in your browser and detects likely sensitive values before they are submitted, pasted, dropped, or uploaded to protected AI chat websites. LeakGuard can redact API keys, passwords, access tokens, client secrets, webhook secrets, database credentials, public IPv4 addresses, CIDR ranges, and supported local text files such as .env, .json, .log, .md, source files, and config files. Sensitive values are replaced with stable placeholders such as [PWM_1], [NET_1], and [PUB_HOST_1], while secure reveal stays inside extension-owned UI. LeakGuard does not use a backend service, telemetry, analytics, cloud scanning, remote secret verification, or remote model calls. LeakGuard is a risk-reduction tool, not a guarantee of complete secret protection. You should still review content before sending it to any AI chat service.