Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

SuperRed

Free#24 of 29 in AI Security Testing Tools

SuperRed: A configurable framework for researchers evaluating attacks, agents, and security claims. Ranked #24 of 29 in AI Security Testing Tools by our editors (6.8/10); pricing: Free plan; best for researchers building composable evaluations.

6.8/10Editor score
SuperRed6.8 Visit SuperRed

At a glance

  • Editor score
    6.8 / 10
  • Pricing
    Free plan
  • Best for
    Researchers building composable evaluations
  • Free plan
    Yes
  • Paid from
    Free
  • Prompt injection tests
    Yes
  • Facts checked
    21 Sep 2026
  • Where it wins

    • Composable attacker, target, and benchmark modules
    • Prompt-injection, jailbreak, agent, and chatbot security testing
    • Budgets, metrics, dashboards, persisted results, and web reports
  • Where it doesn't

    • Self-hosted deployment requires technical ownership
    • Integration coverage centers on LiteLLM-compatible endpoints
    • Results depend on the selected modules, tasks, and security claims

Our verdict on SuperRed

SuperRed is an open-source framework for testing AI system security across chatbots, agents, and assistants. It is designed for red-teamers, AI system builders, and evaluators who need configurable evaluations rather than a fixed collection of tests. Its core structure separates attackers, systems under test, and security benchmarks into interchangeable modules, giving researchers control over how an evaluation is assembled.

The framework’s depth is in its composable evaluation model. Users can define threat models, trust boundaries, attacker access, security claims, custom evaluation tasks, and per-task attacker-model and cost budgets. It supports prompt-injection and jailbreak attack modules, agent and chatbot security testing, data-leakage testing, unsafe-output testing, and custom test cases. Parallel evaluation runs, metrics, persisted results, dashboards, and web reports help organize repeated assessments and communicate findings.

SuperRed is a strong fit for teams that want self-hosted, open-source control over evaluation design and need to compare attacks, targets, and benchmarks within a configurable workflow. Installation is presented through pip, and LiteLLM-compatible endpoints provide the stated integration path. The narrower ecosystem coverage may matter to teams seeking broad native platform connections or a packaged service. It is less suitable for buyers who want a managed testing product with a predefined testing scope; the framework’s output depends on the modules, tasks, threat models, budgets, and security claims selected.

Your product? Our editors can test SuperRed in depth and publish a review, labelled as paid · from $149/mo →

SuperRed pricing

Plans Free planFree Free to use — no paid tier required for the core job.
See plans on rdi.berkeley.edu

SuperRed fact sheet

Free planYes
Paid fromFree
Prompt injection testsYes
Jailbreak testsYes
Data leakage testsYes
Unsafe output testsYes
Custom test casesYes
Deployment modeSelf_hosted
DeploymentSelf-hosted
SupportDocs
Built forSolo, Small business, Mid-market, Enterprise (editorial estimate)
Integrations1 integrations: LiteLLM-compatible endpoints
PricingFree plan
Websiterdi.berkeley.edu
Facts checked21 Sep 2026

SuperRed integrations

SuperRed lists 1 integrations on its own site.

  • LiteLLM-compatible endpoints

Alternatives to SuperRed

See all SuperRed alternatives →

Used SuperRed? Be the first to review it

The editor score above is our own research. What this page doesn't have yet is a reader's view — what you used SuperRed for, what worked and what didn't. No stars are seeded and no review is paid for; an editor reads every one before it appears.

Write a reviewTwo minutes · verified accounts only · read by an editor before it appears

Reviews come only from verified accounts. Sign in or create an account first — your e-mail is never shown.

Your rating

0 characters · at least 80, up to 3,000

Posted from your verified account. Reviews appear after an editor reads them, usually within two working days.

Featured on iTechGuides

Featured on iTechGuides — SuperRed 6.8/10

SuperRed is listed in our AI Security Testing Tools directory. Add the badge to your site — it links back to this page.

<a href="https://www.itechguides.com/products/superred/"><img src="https://www.itechguides.com/best/badge/superred.svg" alt="Featured on iTechGuides" width="230" height="46"></a>

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update