AI red teaming & LLM evaluation
Agentic Radar is an open-source scanner for agent workflows from Zscaler (SPLX). It is released under the Apache-2.0 license and is offered as: CLI, Self-hosted.
Best for
Developers who build agents with LangGraph, CrewAI, n8n, OpenAI Agents or AutoGen and want a free scan of the workflow code with an HTML report
Ownership
Zscaler announced on November 3, 2025 that it has acquired SPLX, which publishes Agentic Radar. The repository README does not mention Zscaler. Source, checked October 21, 2026: zscaler.com (opens in a new tab)
Agentic Radar is a free open-source (Apache-2.0) scanner for agentic workflows, published by SPLX, which is now part of Zscaler. Its scan command reads the code of workflows built with LangGraph, CrewAI, n8n, OpenAI Agents or AutoGen. It lists the agents, tools and MCP servers it finds, maps tools to known vulnerabilities and writes an HTML report with findings tied to OWASP LLM and agentic threat lists. A separate test command sends simulated attacks for prompt injection, PII leakage, harmful content and fake news, but it supports only OpenAI Agents and needs an OpenAI or Azure OpenAI key. The README says static analysis runs locally. The last release is from November 2025. It analyzes workflow code, not 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 | The test command sends simulated prompt injection attacks to OpenAI Agents workflows. | Its test command sends simulated prompt injection attacks to a workflow (OpenAI Agents only) |
| LLM02 Sensitive Information Disclosure | The test command checks for PII leakage. | Its test command checks for PII leakage |
| LLM09 Misinformation | The test command checks for fake news generation. | Its test command checks for fake news generation |
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
SPLX publishes it, and Zscaler announced on November 3, 2025 that it has acquired SPLX. The repository README does not mention Zscaler.
The README lists LangGraph, CrewAI, n8n, OpenAI Agents and AutoGen. The test command with simulated attacks supports only OpenAI Agents.
The README says static analysis and vulnerability mapping run locally. The test command needs an OpenAI or Azure OpenAI key, and optional features such as prompt hardening may send prompts to an LLM.
Agentic Radar is released under the Apache-2.0 license.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Agentic Radar is offered as: CLI, Self-hosted.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Pricing model for Agentic Radar: Free.
Source Source, checked October 21, 2026: splx.ai (opens in a new tab) Checked
Latest release of Agentic Radar: November 27, 2025.
Source Source, checked October 21, 2026: api.github.com (opens in a new tab) Checked
We have no commercial relationship with Zscaler (SPLX).