Help stop your AI agent from leaking secrets.
Clawmont is a security plugin for OpenClaw. Your keys never leave your machine.
Try it live.
Run an attack. See which layer stops it.
The regexes here are the same ones that ship in
packages/plugin/src. No network calls — every verdict runs
in your browser so you can diff what leaks without Clawmont vs. what
gets blocked with it.
Clawmont inspects the payload and emits a signed audit entry before the tool call reaches the model.
Presets auto-load. Free-text mode lets you paste any prompt, tool call, or file path you want to try.
Same regexes that ship in production. Every verdict runs in your browser — no network calls, no plugin instance. Known limitations are published transparently alongside what we do block.
Keys stay local
Your API keys never leave your machine.
11 defense layers
From prompt injection to credential theft.
Tamper-evident audit
Every action logged, hash-chained on disk.
One-time license. Same security on every tier.
Add Guardrails Monitoring for cloud alerts — €9/mo