Skip to content
SPECIFICTION
Get listed

AIRTA Red Team

airtasystems.com

Free plan Open source WebWindowsmacOSLinuxAPISelf-hosted
Visit airtasystems.com
Spec score 9.0 #1 of 29 in AI Security Testing Tools

What it is

AIRTA Red Team is a self-hosted tool for authorized adversarial security assessments of LLMs and LLM-driven applications. It builds test suites from security playbooks, discovers target components and authentication, runs attacks, assesses outcomes, and exports reports. Listed playbooks include OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreak, system prompt exfiltration, and custom scenarios. Strategies include zero-shot, multi-shot, few-shot, iterative, multimodal, jailbreak, and chain-of-thought testing. Targets can be reached through a Playwright browser runner or direct HTTP API transports, including file uploads and tool calls. It can run locally in Docker, behind a firewall, in CI, or against external endpoints for authorized black-box assessments. Runs record prompts, uploads, responses, and tool calls in attack_log.json; pipeline_report.json summarizes categories and severity. Results can be exported to AIRTA Systems for review and regression tracking. The free plan has no license fee or subscription, but users must supply an LLM API key. Assessments focus on observable runtime behavior, not source-code static analysis. The repository says the tool is deprecated and no longer maintained.

Spec sheet

What it does
AIRTA Red Team generates and runs adversarial security tests against LLMs and LLM-driven applications, then assesses whether attacks were exploited or mitigated.Read 15 Oct 2026 · airtasystems.com
Purpose
AIRTA Red Team runs authorized adversarial security assessments against LLMs and LLM-driven applications.Read 4 Oct 2026 · airtasystems.com
Intended users
The product page identifies red teams, whitehat testers and pentesters, and AppSec and MLsec teams as intended users.Read 4 Oct 2026 · airtasystems.com
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.Read 15 Oct 2026 · airtasystems.com
Integrations
The tool can export assessment results to AIRTA Systems through its bulk import API for review and regression tracking.Read 4 Oct 2026 · airtasystems.com
Assessment models
Playbook-specific expert models and a judge model classify attacks as exploited or mitigated and assign severity by category.Read 15 Oct 2026 · airtasystems.com
Assessment scope
The product page says assessments focus on observable runtime behavior rather than source-code static analysis.Read 4 Oct 2026 · airtasystems.com
Attack coverage
Listed playbooks include OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreak, system prompt exfiltration, and custom playbooks.Read 4 Oct 2026 · airtasystems.com
Attack strategies
The documented strategies include zero-shot, few-shot, multi-shot, jailbreak, multimodal, iterative and chain-of-thought testing.Read 15 Oct 2026 · airtasystems.com
Authorization
The product page says to test only systems for which the user has explicit permission.Read 4 Oct 2026 · airtasystems.com
Authorized use
The maker restricts use to systems for which the tester has explicit permission.Read 15 Oct 2026 · airtasystems.com
Capterra pricing listing
Capterra lists AIRTA Systems pricing as contact-vendor, with no free trial and no free version included in that listing.Read 15 Oct 2026 · capterra.com
Company founders
The about page says AIRTA Systems was founded in London by Cindy Ogidi and Bob Morel.Read 15 Oct 2026 · airtasystems.com
Company founding year
LinkedIn lists the company as founded in 2026.Read 15 Oct 2026 · linkedin.com
Company legal name
The product site footer identifies the maker as AIRTA Systems Ltd.Read 15 Oct 2026 · airtasystems.com
Company size
LinkedIn lists AIRTA Systems as having 11–50 employees.Read 15 Oct 2026 · linkedin.com
Company type
LinkedIn classifies AIRTA Systems as a public company in the technology, information and internet industry.Read 15 Oct 2026 · linkedin.com
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.Read 15 Oct 2026 · airtasystems.com
Editable suites
Attack suites are JSON files containing playbooks, categories, prompts and optional multimodal payloads that can be edited in the web interface.Read 15 Oct 2026 · airtasystems.com
Evidence
Runs capture prompts, uploads, responses, and tool calls in attack_log.json and produce pipeline_report.json with category rollups and severity.Read 4 Oct 2026 · airtasystems.com
Evidence files
Runs capture prompts, uploads, responses and tool calls in attack_log.json and summarize results in pipeline_report.json.Read 15 Oct 2026 · airtasystems.com
Execution
Targets can be tested through a Playwright browser runner or direct HTTP API transports, including file uploads and tool calls.Read 4 Oct 2026 · airtasystems.com
Execution transports
Targets can be exercised through a Playwright browser runner or direct HTTP transports named api_document and api_multipart.Read 15 Oct 2026 · airtasystems.com
GetApp listing
GetApp shows no user reviews and places AIRTA Systems in the Other Artificial Intelligence software category.Read 15 Oct 2026 · getapp.com
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.Read 15 Oct 2026 · softwareadvice.com
Integration
The documented integration sends pipeline_report.json to AIRTA Systems through a bulk import API for review, regression tracking and compliance workflows.Read 15 Oct 2026 · airtasystems.com
Limit
Users supply their own LLM API key for test generation and assessment.Read 4 Oct 2026 · airtasystems.com
Limit: assessment coverage
Because the tool focuses on runtime prompts, uploads, responses and tool calls, source-code analysis must be supplied by other tools.Read 15 Oct 2026 · airtasystems.com
Limit: maintenance
The public repository explicitly says the project is no longer maintained and points users to a successor.Read 15 Oct 2026 · github.com
Limit: operating cost
Although the software has no license fee, users still pay for their own LLM API usage because the tool requires their API key.Read 15 Oct 2026 · airtasystems.com
LLM credentials
Users supply their own LLM API key for test generation and assessment.Read 15 Oct 2026 · airtasystems.com
Maintenance status
The GitHub repository says AIRTA Red Team is deprecated and no longer maintained, and directs users to Genbounty LLM Hunter instead.Read 4 Oct 2026 · github.com
Multimodal testing
Multimodal tests can generate file-upload payloads such as hidden-text PDFs, polyglot files and OCR-injection samples.Read 15 Oct 2026 · airtasystems.com
Playbooks
Built-in playbooks cover OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreak techniques, system-prompt exfiltration and custom playbooks.Read 15 Oct 2026 · airtasystems.com
Rating on Capterra
0.0 out of 5 from 0 reviews.Read 15 Oct 2026 · capterra.com
Rating on G2
0.0 out of 5 from 0 reviews.Read 15 Oct 2026 · g2.com
Rating on GetApp
0 out of 5 from 0 reviews.Read 15 Oct 2026 · getapp.com
Repository activity
The repository page shows 14 commits, one star and one fork.Read 15 Oct 2026 · github.com
Repository status
The GitHub repository marks AIRTA Red Team as deprecated, no longer maintained and retained for reference, directing users to Genbounty LLM Hunter.Read 15 Oct 2026 · github.com
Runtime scope
The tool evaluates observable runtime behavior and does not perform source-code SAST.Read 15 Oct 2026 · airtasystems.com
Security policy
AIRTA Systems says it has technical and organizational measures for personal-data security while warning that internet transmission cannot be guaranteed fully secure.Read 15 Oct 2026 · airtasystems.com
Software Advice listing
Software Advice reports no reviews, one custom-quote plan and pricing available on request.Read 15 Oct 2026 · softwareadvice.com
Target discovery
Discovery maps browser selectors or API transports and configures authentication, file uploads and component mapping.Read 15 Oct 2026 · airtasystems.com
Test workflow
The tool generates suites from security playbooks, discovers target components and authentication, runs attacks, assesses outcomes, and exports reports.Read 4 Oct 2026 · airtasystems.com

Plans and prices

AIRTA Red Team Free Open source; no license fee or subscription · Bring your own LLM API key Read 4 Oct 2026 · airtasystems.com
Free Free No license fee; bring your own LLM API key Full pipeline, web UI, playbooks and CLI · self-hosted use Read 15 Oct 2026 · airtasystems.com

Every AIRTA Red Team plan and price →

Strong points and limits

Strong points

  • Supports several security playbooks and attack strategies.
  • Can run locally in Docker, behind a firewall, or in CI.
  • Captures prompts, uploads, responses, and tool calls.
  • Free plan has no license fee or subscription.

Limits

  • Users must provide their own LLM API key.
  • It does not perform source-code static analysis.
  • The tool is deprecated and no longer maintained.

Who it suits

It is intended for red teams, whitehat testers, pentesters, and AppSec or MLsec teams assessing systems they have explicit permission to test.

AIRTA Red Team in depth

Read the full write-up

AIRTA Red Team is a self-hosted runtime assessment tool for authorized testing of LLMs and LLM-powered applications. It suits red teams, pentesters, and AppSec or MLsec groups that need repeatable attack suites and preserved evidence. The zero-license price is attractive, but deprecated maintenance and the required customer-supplied model key make it a cautious choice for new, long-lived programs.

Overview

AIRTA Red Team converts security playbooks into executable suites, identifies target components and authentication, performs attacks, evaluates the responses, and exports reports. This workflow examines observable behavior at runtime rather than source-code weaknesses, so it complements rather than replaces static analysis. Testing is intended only for systems for which you have explicit authorization.

Deployment can be local Docker, inside a firewall, in continuous integration, or against an external endpoint during an authorized black-box assessment. Browser applications can run through a Playwright runner; direct HTTP transports cover APIs, file uploads, and tool calls. That combination is practical for mixed application estates, although operating a self-hosted, deprecated project places maintenance responsibility on your team.

Key features

Playbooks and attack strategies

Built-in coverage spans OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreak, system-prompt exfiltration, and custom playbooks. Tests include prompt injection, jailbreak, and data-leakage scenarios, with custom cases for organization-specific threats. Zero-shot, few-shot, multi-shot, iterative, multimodal, jailbreak, and chain-of-thought strategies let a tester vary how attacks are delivered instead of relying on one fixed probe style.

Execution and evidence

Runs record prompts, uploads, responses, and tool calls in attack_log.json. A companion pipeline_report.json provides category rollups and severity, giving reviewers an auditable record rather than only a pass-or-fail result. Results can be bulk-imported to AIRTA Systems for review and regression tracking, which is useful when a team already uses that service.

Operational constraint

Test generation and assessment require your own LLM API key. That keeps the software license-free but leaves model access, credentials, and associated usage charges to the operator. The project is also deprecated and no longer maintained; its repository points users toward Genbounty LLM Hunter, a serious concern for teams expecting fixes or current integrations.

Pricing

PlanPriceWhat it includesAIRTA Red TeamfreeOpen source; no license fee or subscription; bring your own LLM API keyThere are no paid tiers, seat charges, or subscription renewals. The trade-off is that free software does not mean free operation: you provide the model credential and run the deployment yourself. This plan fits security teams able to maintain infrastructure and control their test endpoints; organizations seeking vendor support, hosted execution, or an actively maintained commercial service should look elsewhere.

Platforms

AIRTA Red Team supports API, Linux, macOS, web, and Windows environments. Its self-hosted deployment model and Docker option make it suitable for CI and network-isolated installations, while Playwright and HTTP transports address browser and API targets. Platform support does not remove the need to manage the runtime, credentials, and authorized access.

Who it's for

Red teams and whitehat testers can use the playbook and strategy range to structure adversarial campaigns. Pentesters benefit from browser and API execution plus exported evidence for client reporting. AppSec and MLsec teams get repeatable runtime checks, severity rollups, and bulk import for regression review. It is a poor fit for teams that require source-code analysis, guaranteed maintenance, or a managed service.

Pros and cons

Pros

No license fee: the open-source free plan removes software subscription cost.

Broad adversarial coverage: recognized LLM and agent playbooks, custom playbooks, and multiple attack strategies support varied threat models.

Flexible targeting: Playwright and direct HTTP transports handle browser flows, APIs, uploads, and tool calls.

Useful run evidence: captured interaction logs and severity reports support review and regression tracking.

Cons

Deprecated and unmaintained: ongoing fixes and compatibility should not be assumed.

Bring your own model key: operators carry credential management and LLM usage costs.

Runtime-only scope: it cannot stand in for source-code static analysis.

Self-hosting burden: deployment, security controls, and authorized access remain your responsibility.

Alternatives

F5 BIG-IP APM is a paid, trial-available option for teams needing a broad multi-platform access-management product rather than a free open-source red-team workflow.

OpenSecureAI Scanner suits teams wanting a freemium service with a Pro plan at $49 a month, including 50,000 API requests monthly and hosted remediation features.

Project Moonshot is another free, cross-platform choice for organizations preferring that project’s approach to AI security testing.

Promptfoo is preferable when a freemium tool with a Community plan offering 10k red-team probes per month and broad provider integrations meets your evaluation needs.

PromptGuard fits teams seeking hosted scan quotas, with a free tier capped at 20,000 scans a month and one project.

PyRIT is a free open-source framework for users prepared to provide a Python environment and configured AI endpoints.

Augustus is free Apache 2.0 software for teams wanting a Linux, macOS, or Windows self-hosted option, with provider credentials potentially required.

Basilisk is free AGPL-3.0 software delivered as CLI, desktop, Docker, or source distributions for authorized use.

Verdict

Choose AIRTA Red Team if you are an experienced security team that wants broad, evidence-rich runtime testing at no license fee and can operate deprecated self-hosted software with your own LLM key. Look elsewhere if maintenance, managed delivery, source-code analysis, or predictable vendor support is central to your security program.

Verdict

AIRTA Red Team offers a broad runtime assessment workflow and detailed run evidence at no license fee. Its deprecated, unmaintained status and bring-your-own API key requirement are important constraints.

Where Specifiction places it

Alternatives to AIRTA Red TeamAll alternatives →