AI red teaming & LLM evaluation

SPLX: AI red teaming platform

SPLX is an AI red teaming platform from Zscaler. It is a commercial product offered as: SaaS, On-prem. Pricing model: contact sales.

  • Last reviewed

Best for

Teams that want a managed platform to run automated red teaming against AI applications, with on-prem or hybrid deployment available on the Enterprise plan

Ownership

Zscaler announced on November 3, 2025 that it has acquired SPLX. Source, checked October 21, 2026: zscaler.com (opens in a new tab)

Consider instead if

  • You want a free scanner you run yourself from the command line, with no sales process. See garak.

What SPLX does

SPLX is a commercial platform for red teaming AI systems, now part of Zscaler. Its AI Red Teaming product, called Probe, runs automated tests that use generative AI to craft attacks against a target application, drawing on an attack database and the customer's own datasets. The docs describe a customizable set of probes, a compliance view that includes the OWASP LLM Top 10 2025, a PDF report for each test run and remediation help such as prompt hardening. SPLX also sells runtime protection and publishes Agentic Radar, a free open-source scanner for agent workflows, which is a separate product. The pricing page shows plan names and credits but no prices, and quotes come through sales.

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.

Ownership
Zscaler announced on November 3, 2025 that it has acquired SPLX. Source, checked October 21, 2026: zscaler.com (opens in a new tab)
Latest release
Not documented in the sources we checked
Pricing model
Contact sales: Plans named: Free, Professional and Enterprise. Professional lists 2000 credits per month. No prices are shown; Professional and Enterprise have a Get a Quote button. (as listed on October 21, 2026; check the vendor for current pricing) Source, checked October 21, 2026: splx.ai (opens in a new tab)
Attestations or disclosure
ISO 27001 certified; SOC 2 compliant; GDPR compliant; CCPA compliant Source, checked October 21, 2026: splx.ai (opens in a new tab)

Capabilities

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

Integrations

Where SPLX 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 SPLX covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased 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

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 SPLX, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM01 Prompt Injection Docs name a Jailbreak probe among the probe runs. Includes a Jailbreak probe among its example probe runs
LLM02 Sensitive Information Disclosure Docs name a Context Leakage probe among the probe runs. Includes a Context Leakage probe among its example probe runs

Alternatives and related tools

More in AI red teaming & LLM evaluation, ranked within the category by Coverage Score.

garak

NVIDIA

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

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

Coverage Score 82 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM09 Misinformation

Reviewed

Giskard

Giskard AI

Open sourceApache-2.0 Freemium
  • Library
  • Self-hosted
  • SaaS
  • On-prem

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

Coverage Score 81 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM09 Misinformation

Reviewed

Promptfoo

OpenAI (Promptfoo)

Open sourceMIT Freemium
  • CLI
  • Library
  • Self-hosted
  • SaaS
  • On-prem

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

Coverage Score 80 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM09 Misinformation

Reviewed

SPLX FAQ

Who owns SPLX?

Zscaler announced on November 3, 2025 that it has acquired SPLX, and the splx.ai site carries a banner saying SPLX is now part of Zscaler.

Is SPLX open source?

The Probe red teaming platform is a commercial product with no public repository. SPLX publishes a separate open-source scanner for agent workflows called Agentic Radar.

How much does SPLX cost?

The pricing page names Free, Professional and Enterprise plans and lists 2000 credits per month for Professional, but it shows no prices. Professional and Enterprise have a Get a Quote button.

Key facts you can cite

We have no commercial relationship with Zscaler (SPLX).

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.