Best AI Red Teaming CompaniesAn independent guide to AI red teaming vendors

Compare vendors / Spikee

Spikee

Open-source prompt injection testing kit

Open source

Spikee builds targeted prompt injection and jailbreak datasets and tests them against LLMs, guardrails and applications. WithSecure Labs released it, and it is now maintained by Reversec, the offensive security consultancy spun out of WithSecure in Apr 2025. The latest release, 0.9.4, shipped on Nov 3, 2026.

Best for: Pentesters checking prompt injection resilience of a specific app or guardrail.

Open source (Apache-2.0), maintained by Reversec Labs

  • – Maps to OWASP
  • – Maps to MITRE ATLAS
  • – Maps to the EU AI Act
  • – SOC 2 or ISO 27001
Visit Spikee

Facts checked November 9, 2026 against the sources listed below. Spikee does not pay to appear here.

1 Legal nameSpikee (Simple Prompt Injection Kit for Evaluation and Exploitation)
2 HeadquartersNot disclosed
3 Founded2025
4 TeamNot disclosed
5 What they testLLM apps, Prompt injection and jailbreaks, Data leakage
6 FrameworksNot disclosed
7 CertificationsNot disclosed
8 Published pricesFree (Apache-2.0)
9 Customers and partnersNot disclosed

Worth knowing before you sign

  • Small community (about 270 GitHub stars) and still pre-1.0.

Go to Spikee's site

Sources

  1. GitHub: ReversecLabs/spikee
  2. PyPI: spikee
  3. WithSecure Labs: tool page
  4. PR Newswire: Reversec launch

Work at Spikee? Send corrections with a source to editors@bestairedteamingcompanies.com. We fix verified errors within five business days.

Compare with

  • garak Open-source LLM vulnerability scanner
  • PyRIT Microsoft’s open-source red teaming framework for generative AI
  • Promptfoo (open source) Open-source CLI for LLM evals and red teaming
  • DeepTeam Open-source LLM red teaming framework from Confident AI
  • Giskard (open source) Open-source evals and red teaming library for agents