AIRTA Red Team runs authorized adversarial security assessments against LLMs and applications driven by them. It builds test suites from security playbooks, discovers target components and authentication, executes attacks, assesses outcomes, and exports reports. Listed coverage includes OWASP LLM, OWASP Agent, MITRE ATLAS, jailbreaks, system prompt exfiltration, and custom playbooks. 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. The tool can run locally in Docker, behind a firewall, in CI, or against external endpoints for authorized black-box testing. Run evidence includes prompts, uploads, responses, and tool calls in attack_log.json; pipeline_report.json provides category rollups and severity. Results can be exported to AIRTA Systems for review and regression tracking. The open-source tool has no license fee or subscription, but users must provide an LLM API key. Its repository says it is deprecated and no longer maintained.
Who it is for
It is aimed at red teams, whitehat testers, pentesters, and AppSec or MLsec teams assessing systems they have explicit permission to test. It focuses on observable runtime behavior rather than source-code static analysis.
What is good
- Covers named LLM security playbooks
- Supports browser and direct HTTP API testing
- Can run locally, in CI, or behind a firewall
- Records attack evidence and report severity
What to know first
- Deprecated and no longer maintained
- Requires users' own LLM API key
- Does not perform source-code static analysis
- Testing requires explicit authorization
Verdict
AIRTA Red Team offers broad runtime assessment workflows and report evidence without a license fee. Its deprecated, unmaintained status and required API key are important constraints.
AIRTA Red Team plans and pricing
All plansCompared on AI security testing tools
- Free plan
- Yes
- Prompt injection tests
- Yes
- Jailbreak tests
- Yes
- Data leakage tests
- Yes
- Custom test cases
- Yes
- Deployment mode
- self_hosted
