AI red teaming & LLM evaluation
Spikee is an open-source prompt injection testing toolkit from Reversec. It is released under the Apache-2.0 license and is offered as: CLI, Self-hosted.
Best for
Security teams that want a free toolkit for building and running prompt injection test datasets against an LLM app or a guardrail
Ownership
Reversec's launch article, datelined April 28, 2025, says Reversec was formerly known as the Consulting unit of WithSecure. It does not say who owns Reversec. Source, checked October 21, 2026: reversec.com (opens in a new tab)
Consider instead if
Spikee is a Python toolkit for checking how well language models, guardrails and LLM applications resist prompt injection and jailbreaking. You generate a dataset from seed files, point a target module at the system under test, run attacks, and use a judge to decide whether each attempt succeeded. The README lists plugins that transform payloads, single-turn and multi-turn attacks, canary, regex and LLM judges, custom modules, a web UI and results analysis tools. It installs with pip, and the repository uses the Apache-2.0 license, so there is no license fee. It is a test kit you run on demand, not a filter for live traffic.
This summary is our own wording of the sourced facts on this page.
Each value links to the page that states it, with the date we checked it.
As documented by the vendor or project. The tag is our label from a controlled vocabulary.
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.
| Layer | Role | How it applies | Based on |
|---|---|---|---|
| L4 Testing Testing and red teaming | Primary | Attack and evaluate models, apps and agents on purpose, before release and after every change, to find what the other layers miss. | Follows its category, AI red teaming & LLM evaluation |
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.
| Risk | How it applies | Based on |
|---|---|---|
| LLM01 Prompt Injection | Generates and runs prompt injection and jailbreak test cases against a target. | Tests LLMs, guardrails and applications for resistance to prompt injection; Tests for resistance to jailbreaking, using jailbreak seed files in its datasets |
| LLM02 Sensitive Information Disclosure | Its stated focus includes data exfiltration threats against LLM applications. | Focuses on cybersecurity threats such as data exfiltration and XSS |
| LLM07 System Prompt Leakage | Ships a seed set aimed at system message extraction. | Includes a seed set for system message extraction |
More in AI red teaming & LLM evaluation, ranked within the category by Coverage Score.
NVIDIA
Probes language models and LLM apps for prompt injection, jailbreaks, data leakage and more.
Best for: Teams that want a free command-line scanner they can point at any model or LLM endpoint before release
Reviewed
Giskard AI
Generates adversarial test suites for LLM agents and RAG apps, runs them and reports failures by threat type.
Best for: Python teams that want a free library to scan an LLM agent or RAG app for prompt injection and harmful output, and to write pass or fail checks for it
Reviewed
OpenAI (Promptfoo)
Runs evals and red team scans against LLM apps from a CLI or CI pipeline and writes a vulnerability report.
Best for: Developer teams that want one open-source CLI for both prompt evals and red teaming, run locally and in CI
Reviewed
Yes. Spikee is released under the Apache-2.0 license, and the code is on GitHub at ReversecLabs/spikee.
The README says it tests LLMs, guardrails and LLM applications for resistance to prompt injection and jailbreaking, using targets, plugins, attacks and judges you can extend.
The README gives pip install spikee, followed by spikee init in a workspace folder. Providers that use native SDKs need extras, for example pip install spikee[all].
Spikee is released under the Apache-2.0 license.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Spikee is offered as: CLI, Self-hosted.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Pricing model for Spikee: Free.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Spikee had 268 GitHub stars on October 21, 2026.
Source Source, checked October 21, 2026: api.github.com (opens in a new tab) Checked
We have no commercial relationship with Reversec.