AI red teaming & LLM evaluation
Lakera Red is an automated and expert AI red teaming offering from Check Point. It is a commercial product offered as: Managed service. Pricing model: contact sales.
Best for
Ownership
Check Point completed its acquisition of Lakera in the fourth quarter of 2025. Source, checked October 21, 2026: checkpoint.com (opens in a new tab)
Lakera Red now names two things under Check Point, which completed its purchase of Lakera in late 2025. The product page sells automated red teaming: a continuous workflow that scans AI apps and agents for safety, security and responsible AI failures, behind a Start for free button. The docs describe the expert assessment, four steps from mapping the application to a report with severity ratings and fixes, pitched as finding what traditional testing misses. The expert scope is the more specific of the two: context extraction, instruction override, content injection, service disruption, and indirect poisoning through RAG ingestion or integrations. Neither page gives a price, free tier terms or a mapping of findings to OWASP, so ask which of the two you are buying and what the report covers.
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 | Expert-led tests cover prompt injection and jailbreaks. | Security testing covers prompt injection; Security testing covers jailbreaks; Expert service tests indirect poisoning through external data sources, RAG ingestion or integrations |
| LLM02 Sensitive Information Disclosure | Security testing covers data leakage. | Security testing covers data leakage |
| LLM06 Excessive Agency | Covers tool-using agents and tests for unauthorized actions. | Covers agentic workflows with multi-step, tool-using agents, and tests for unauthorized actions |
| LLM07 System Prompt Leakage | Context extraction tests try to pull out hidden system prompts. | Context extraction tests try to pull out hidden system prompts, credentials or sensitive configuration |
| LLM08 Vector and Embedding Weaknesses | The expert assessment tests indirect poisoning through RAG ingestion, the knowledge base poisoning path in LLM08. | Security testing covers prompt injection; Expert service tests indirect poisoning through external data sources, RAG ingestion or integrations |
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
Both. The product page headlines automated red teaming, a continuous workflow that scans AI apps and agents. The docs describe an expert-led assessment in four steps, from application enumeration to risk assessment and reporting, which you arrange by contacting the team.
The docs list indirect poisoning through external data sources, RAG ingestion or integrations among the expert assessment's tests, next to context extraction, instruction override, content injection and service disruption.
Check Point completed its acquisition of Lakera in the fourth quarter of 2025, and the docs now call the service Check Point AI Red Teaming.
No price is published on the pages we read. The product page offers Book a demo and Contact sales.
Lakera Red is closed source (proprietary).
Source Source, checked October 21, 2026: docs.lakera.ai (opens in a new tab) Checked
Lakera Red is offered as: Managed service.
Source Source, checked October 21, 2026: docs.lakera.ai (opens in a new tab) Checked
Pricing model for Lakera Red: Contact sales.
Source Source, checked October 21, 2026: lakera.ai (opens in a new tab) Checked
Status of Lakera Red: Active.
Source Source, checked October 21, 2026: lakera.ai (opens in a new tab) Checked
We have no commercial relationship with Check Point (Lakera).