AIRTA Red Team
airtasystems.com
- Free plan
- Open source
- Windows
- macOS
- Linux
- Web
- API
- Self-hosted
What AIRTA Red Team is
AIRTA Red Team is a self-hosted tool for authorized adversarial assessments of LLMs and applications that use them. It builds test suites from security playbooks, identifies target components and authentication, runs attacks, assesses outcomes and exports reports. Coverage includes OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreaks, system-prompt exfiltration and custom playbooks. Testing strategies include zero-shot, multi-shot, few-shot, iterative, multimodal, jailbreak and chain-of-thought approaches. Targets can be tested through a Playwright browser runner or direct HTTP API transports, including file uploads and tool calls. The tool can run locally in Docker, behind a firewall, in CI, or against external endpoints for authorized black-box testing. Runs capture prompts, uploads, responses and tool calls in attack_log.json; pipeline_report.json summarizes categories and severity. Results can be sent to AIRTA Systems for review and regression tracking. Users must supply their own LLM API key, and assessments focus on observable runtime behavior rather than static source-code analysis. The repository says the tool is deprecated and no longer maintained, and directs users to Genbounty LLM Hunter instead.
Who it suits
The product page identifies red teams, whitehat testers, pentesters, and AppSec and MLsec teams as intended users. Testing should be limited to systems for which the user has explicit permission.
Good to know, and what to watch
- Includes OWASP LLM, OWASP Agent and MITRE ATLAS playbooks
- Supports browser-runner and direct HTTP API testing
- Captures prompts, uploads, responses and tool calls
- Can run locally, behind a firewall or in CI
- Users must provide their own LLM API key
- Focuses on runtime behavior, not static source-code analysis
- Repository says the tool is deprecated and unmaintained
Plans
Every plan and priceAIRTA Red Team
Free
Free plan
Getting started
- Open the AIRTA Red Team website
- Choose a self-hosted deployment such as local Docker, firewall, CI, or an external authorized endpoint
- Provide your own LLM API key
- Connect a target through the Playwright runner or direct HTTP API
- Select a security playbook and attack strategy
- Run the assessment and export the generated reports
Limits to check
The free plan has no license fee or subscription, but it requires your own LLM API key. Assessments cover observable runtime behavior rather than source-code static analysis, and the repository says the project is no longer maintained.
The Club's review
AIRTA Red Team is an open-source assessment tool for teams probing LLMs and LLM-powered applications through authorized attacks. It is aimed at red teams, pentesters, and AppSec or MLsec practitioners who want repeatable runtime tests and detailed run records. Its broad testing workflow is appealing, but its deprecated, unmaintained status makes it hard to recommend for ongoing use.
Overview
The tool builds test suites from security playbooks, identifies target components and authentication, runs attacks, evaluates outcomes, and exports reports. Its focus is observable runtime behavior, so it can expose problems that appear in interaction with a model or application; it does not provide source-code static analysis. Testing should be limited to systems for which you have explicit permission.
Deployment can be local in Docker, behind a firewall, in CI, or against external endpoints for authorized black-box assessments. Targets can be reached through a Playwright browser runner or direct HTTP API transports, including file uploads and tool calls. This gives teams a way to assess both browser-facing applications and API targets, but test generation and assessment require users to supply their own LLM API key.
Key features
Playbooks and attack strategies
Coverage includes OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreak, system-prompt exfiltration, and custom playbooks. Available strategies include zero-shot, few-shot, multi-shot, iterative, multimodal, jailbreak, and chain-of-thought testing. The variety helps security teams shape assessments around different attack patterns, while custom playbooks allow them to add cases relevant to their own targets.
Execution and evidence
Runs record prompts, uploads, responses, and tool calls in attack_log.json. The tool also creates pipeline_report.json, with category rollups and severity. Keeping both interaction records and summarized findings can make review and follow-up more concrete than a result list alone. Results can also be exported to AIRTA Systems through its bulk import API for review and regression tracking.
Pricing
AIRTA Red Team costs nothing. The open-source plan has no license fee or subscription, and there is no paid tier described. That makes it accessible for teams prepared to deploy and operate it themselves, but the price does not cover LLM usage: users must bring their own API key for generation and assessment.
Platforms
AIRTA Red Team supports API, Linux, macOS, web, and Windows. Its self-hosted deployment options are useful for teams that need to run assessments within their own environments, including behind a firewall or in CI.
Who it's for
Red teams, whitehat testers, pentesters, and AppSec or MLsec teams are the clearest fit, particularly when they need to assess runtime behavior across browser and API targets. It is less suitable for teams seeking source-code analysis or a maintained product they can rely on for continuing security work. The maker's permission requirement also matters: this tool is for systems the tester is explicitly authorized to assess.
Pros and cons
- Pros: Playbooks and attack strategies cover several established security frameworks and attack styles, with custom playbooks for tailored cases.
- Pros: Browser and HTTP API execution, including uploads and tool calls, supports different target interfaces.
- Pros: Captured run evidence and severity rollups give teams material for review and regression tracking.
- Pros: The open-source plan has no license fee or subscription.
- Cons: The repository marks the project deprecated and no longer maintained, a significant concern for security tooling.
- Cons: Users must provide their own LLM API key, and usage costs are separate from the free software.
- Cons: Runtime-only assessment leaves source-code static analysis outside its scope.
Alternatives
AI Security Testing Tools is a broader directory for comparing options in this category. Consider OpenSecureAI Scanner if a freemium option with a published Pro tier suits your needs: Pro costs $49 a month and includes 50,000 API requests per month, a 120-request-per-minute limit per key, hosted AI remediation and LLM Gateway completions, and priority email support.
PyRIT is another free, open-source framework; choose it if a Python environment and configured AI endpoints fit your workflow. Augustus is a free Apache 2.0-licensed option, with provider credentials potentially needed for API use. Basilisk offers free AGPL-3.0 software through CLI, desktop, Docker, or source distribution, for authorized use only. Promptfoo is worth comparing if its free Community plan's 10k red-team probes per month and local or self-hosted operation suit your requirements. PromptGuard has a free plan capped at 20,000 scans a month, one API key, one project, and 24-hour log retention; its Team plan costs $19 a month.
F5 BIG-IP APM is a paid alternative with a free trial and a perpetual-license option for BIG-IP Virtual Editions, hardware, or hybrid environments. Project Moonshot is another free alternative to consider.
Verdict
AIRTA Red Team is best suited to authorized security teams that want a free, self-hosted way to run varied LLM runtime attacks and retain structured evidence. Its strongest reason to choose it is the combination of playbook-driven testing, flexible execution, and detailed run records. Its main reason to look elsewhere is decisive: the project is deprecated and no longer maintained, making an active alternative a safer choice for ongoing assessments.
The verdict
AIRTA Red Team offers self-hosted testing workflows and detailed run evidence for authorized LLM assessments. Its deprecated, unmaintained status is an important consideration before adopting it.
Questions people ask
Is AIRTA Red Team free?
Yes. The listed plan is free at no cost, with no license fee or subscription.
Which platforms does it support?
AIRTA Red Team is listed for API, Linux, macOS, web, and Windows.
What testing does it cover?
It lists prompt-injection, jailbreak, data-leakage, and custom test cases, plus OWASP LLM, OWASP Agent, MITRE ATLAS, system-prompt exfiltration, and custom playbooks.
Can it run without providing an LLM key?
No. Users supply their own LLM API key for test generation and assessment.
Is AIRTA Red Team maintained?
The GitHub repository says it is deprecated and no longer maintained, and directs users to Genbounty LLM Hunter.
What the maker publishes
- Assessment models
- Playbook-specific expert models and a judge model classify attacks as exploited or mitigated and assign severity by category. source
- Assessment scope
- The product page says assessments focus on observable runtime behavior rather than source-code static analysis. source
- Attack coverage
- Listed playbooks include OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreak, system prompt exfiltration, and custom playbooks. source
- Attack strategies
- Strategies include zero-shot, multi-shot, jailbreak, multimodal, few-shot, iterative, and chain-of-thought testing. source
- Attack strategies
- The documented strategies include zero-shot, few-shot, multi-shot, jailbreak, multimodal, iterative and chain-of-thought testing. source
- Authorization
- The product page says to test only systems for which the user has explicit permission. source
- Authorized use
- The maker restricts use to systems for which the tester has explicit permission. source
- Capterra pricing listing
- Capterra lists AIRTA Systems pricing as contact-vendor, with no free trial and no free version included in that listing. source
- Company founders
- The about page says AIRTA Systems was founded in London by Cindy Ogidi and Bob Morel. source
- Company founding year
- LinkedIn lists the company as founded in 2026. source
- Company legal name
- The product site footer identifies the maker as AIRTA Systems Ltd. source
- Company size
- LinkedIn lists AIRTA Systems as having 11–50 employees. source
- Company type
- LinkedIn classifies AIRTA Systems as a public company in the technology, information and internet industry. source
- Deployment
- The site describes running the tool locally in Docker, behind a firewall, in CI, or against external endpoints for authorized black-box assessments. source
- Deployment
- The maker documents local Docker deployment with python start.py, CLI operation with main.py, CI use, behind-firewall staging and authorized external black-box testing. source
- Documentation
- The maker provides a support documentation page with article search and category filters, but the page currently shows a loading posts area rather than a visible Red Team manual. source
- Editable suites
- Attack suites are JSON files containing playbooks, categories, prompts and optional multimodal payloads that can be edited in the web interface. source
- Evidence
- Runs capture prompts, uploads, responses, and tool calls in attack_log.json and produce pipeline_report.json with category rollups and severity. source
- Evidence files
- Runs capture prompts, uploads, responses and tool calls in attack_log.json and summarize results in pipeline_report.json. source
- Execution
- Targets can be tested through a Playwright browser runner or direct HTTP API transports, including file uploads and tool calls. source
- Execution transports
- Targets can be exercised through a Playwright browser runner or direct HTTP transports named api_document and api_multipart. source
- GetApp listing
- GetApp shows no user reviews and places AIRTA Systems in the Other Artificial Intelligence software category. source
- Independent-review availability
- G2, Capterra, GetApp and Software Advice pages opened for AIRTA Systems each show zero or no user reviews, so there is no repeated reviewer praise or complaint pattern to report. source
- Integration
- The documented integration sends pipeline_report.json to AIRTA Systems through a bulk import API for review, regression tracking and compliance workflows. source
Checked against the maker's pages on 15 Oct 2026.