247  rebuff(1) - Kailash Tool Reference

247.1 rebuff

rebuff - Rebuff — prompt-injection detector with a canary-token leakage check and multi-stage defence.

Layer DEFENCE
Category d-01-runtime-defence
Safety class safe
Licence Apache-2.0
Upstream github.com/protectai/rebuff

247.1.1 NAME

rebuff - Rebuff — prompt-injection detector with a canary-token leakage check and multi-stage defence.

247.1.2 SYNOPSIS & usage

Derived from the upstream README at generation time; verify against --help where the tool is installed.

pip install rebuff
cd server

247.1.3 DESCRIPTION (upstream)

“MD013”: { “code_blocks”: false, “tables”: false }, “MD033”: false, “MD041”: false } –> Rebuff is designed to protect AI applications from prompt injection (PI) attacks through a multi-layered defense. Playground • Discord • Features • Installation • Getting started • Self-hosting • Contributing • Rebuff is still a prototype and cannot provide 100% protection against prompt injection attacks! Rebuff offers 4 layers of defense: - Heuristics: Filter out potentially malicious input before it reaches the LLM. - LLM-based detection

247.1.4 CONFIGURATION (detected)

Config-surface markers detected in the upstream README (5 matches, e.g. javascript_tests.yaml, javascript_tests.yaml). A full config reference page for this tool is queued under the config-page policy — this line is the detection record, not the page.

247.1.5 SEE ALSO

ref: pin - verified 2026-10-14