AI Defense Stack

LLM firewalls & guardrails

Rebuff: archived prompt injection detector prototype

Rebuff is an archived prompt injection detector prototype from Palo Alto Networks (Protect AI). It is open source under the Apache-2.0 license and is offered as: Library, Self-hosted, API.

  • Last reviewed
Visit Rebuff (opens in a new tab) Documentation (opens in a new tab) Source code (opens in a new tab)
Open sourceApache-2.0 Archived Layer 6: Runtime guardrails

Best for

Researchers and builders who want a small, readable reference implementation of layered prompt injection detection with canary tokens

Ownership

Palo Alto Networks announced on July 22, 2025 that it completed its acquisition of Protect AI. Source, checked October 21, 2026: paloaltonetworks.com (opens in a new tab)

Consider instead if

  • You want an open-source guardrails library that is still in active development. See NeMo Guardrails.
  • You prefer a hosted API that screens prompts for you. See Lakera Guard.

What Rebuff does

Rebuff is an open-source prompt injection detector from Protect AI that its README calls a self-hardening prototype. It layers four defenses: heuristics that filter input before it reaches the model, a dedicated LLM that analyzes prompts, a vector database of embeddings from earlier attacks, and canary tokens that detect leakage of prompt content. You can use the Python SDK or self-host a server that needs OpenAI, Supabase and a vector database such as Pinecone or Chroma. It is Apache-2.0 licensed and free. The repository was archived on May 16, 2025 and is read-only, and the README states that it cannot provide 100 percent protection against prompt injection.

This summary is our own wording of the sourced facts on this page.

Key facts

Each value links to the page that states it, with the date we checked it.

Vendor
Palo Alto Networks (Protect AI) Source, checked October 21, 2026: paloaltonetworks.com (opens in a new tab)
Status
Archived Source, checked October 21, 2026: api.github.com (opens in a new tab)
Ownership
Palo Alto Networks announced on July 22, 2025 that it completed its acquisition of Protect AI. Source, checked October 21, 2026: paloaltonetworks.com (opens in a new tab)
Open source
Yes: Apache-2.0 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Repository
github.com Source, checked October 21, 2026: api.github.com (opens in a new tab)
GitHub stars
1,531 as of October 21, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest push
August 7, 2024 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest release
Not documented in the sources we checked
Deployment
Library, Self-hosted, API Source, checked October 21, 2026: github.com (opens in a new tab)
Pricing model
Free Source, checked October 21, 2026: github.com (opens in a new tab)
Website
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
Documentation
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
API reference
Not documented in the sources we checked
Quickstart
Not documented in the sources we checked
Security page
Not documented in the sources we checked
Attestations or disclosure
Not documented in the sources we checked

Capabilities

As documented by the vendor or project. The tag is our label from a controlled vocabulary.

Where Rebuff fits in our AI security layers

Our analysis

Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.

AI security layers that Rebuff covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased on
L6 Runtime Runtime guardrails Primary Screen what goes into and comes out of a model in live traffic, and limit abuse of the model endpoint. Follows its category, LLM firewalls & guardrails

OWASP LLM Top 10 mapping

Our analysis

The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.

OWASP LLM risks mapped to Rebuff, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM01 Prompt Injection Heuristic and LLM-based checks screen incoming prompts for injection attempts. Filters potentially malicious input with heuristics and a dedicated LLM check before it reaches the model; Stores embeddings of earlier attacks in a vector database to recognize similar prompts later
LLM07 System Prompt Leakage Canary tokens flag when prompt content leaks into a response. Adds canary tokens to prompts to detect leakage of prompt content

Not mapped in our analysis: LLM02, LLM05, LLM09, LLM10. These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.

Alternatives and related tools

More in LLM firewalls & guardrails, ranked within the category by Coverage Score.

NVIDIA NeMo Guardrails

NVIDIA

Open sourceApache-2.0
  • Library
  • Self-hosted
  • API

Adds programmable input, dialog, retrieval, execution and output rails to LLM applications.

Best for: Teams that want to script rules for one LLM application in Python and run them in their own infrastructure

Coverage Score 76 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM05 Improper Output Handling
  • LLM06 Excessive Agency

Reviewed

Portkey AI Gateway

Palo Alto Networks (Portkey)

Open sourceMIT Freemium Now Prisma AIRS AI Gateway
  • SaaS
  • Self-hosted
  • API

Routes LLM traffic through one gateway API and runs input and output guardrail checks on each request.

Best for: Teams that want a single gateway for several LLM providers with guardrail checks, available as open source or as a hosted service

Coverage Score 69 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM05 Improper Output Handling
  • LLM09 Misinformation

Reviewed

Kong AI Gateway

Kong

Open sourceApache-2.0
  • Self-hosted
  • SaaS
  • API

Routes LLM traffic through Kong with prompt guards, PII sanitization, spend limits and observability.

Best for: Teams that already run Kong as an API gateway and want LLM routing and prompt controls on the same data plane

Coverage Score 65 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM10 Unbounded Consumption

Reviewed

Rebuff FAQ

Is Rebuff open source?

Yes. It is released under the Apache-2.0 license, and the code is on GitHub at protectai/rebuff.

Is Rebuff still maintained?

No. The GitHub repository was archived by its owner on May 16, 2025 and is read-only, and the README calls the project a prototype.

What does Rebuff need to self-host?

The README says self-hosting needs OpenAI, Supabase and a vector database such as Pinecone or Chroma, plus an environment file with the keys.

Key facts you can cite

We have no commercial relationship with Palo Alto Networks (Protect AI).

Sources & last reviewed

Last reviewed . We compile from the vendors' own public pages and repositories and we do not run the products. Source links open in a new tab. Found a mistake? Report a correction.