Ship AI agents.
Not attack surfaces.

Prompt injection is when someone hides instructions inside content your AI reads — a webpage, an email, a file — hoping your model follows them instead of you. AiDren screens every request before it reaches your model, catching injected instructions before they can hijack your agent.

The proxy layer itself adds about 5 ms. On top of that, requests that need screening get one classification call — usually 200–500 ms, which runs before your request reaches OpenAI, Anthropic, or Mistral, so it overlaps nothing. Short, clearly-benign messages skip the classification call entirely. Model-file scans and egress reports add nothing to your chat traffic.

OpenAI, Anthropic, and Mistral today, with the same drop-in proxy pattern for all three. More providers are coming.

Hugging Face Hub and GitHub: release assets and raw files. Route the download through AiDren and it's scanned for malicious code before it reaches disk, across pickle (including ones wrapped inside a torch.save ZIP), safetensors, GGUF, ONNX, joblib, and Keras. Non-model files pass straight through.

Yes. Output scanning checks every response for system-prompt leaks and common data-leak patterns, including emails, card numbers, IBANs, phone numbers, API keys, and private keys, before it reaches your app. You choose per key whether a hit gets redacted or the whole response blocked, and whether prompts get the same check.

Yes. Custom policies let you attach term, regex, topic, and threshold rules to any proxy key: block a specific phrase, cap message length, flag a topic your model shouldn't discuss. The built-in judge still runs underneath; a policy adds to it, it doesn't replace it.

Yes, on every plan, with unlimited seats. Invite teammates by email; they get their own login into the same account. An audit log (with CSV export) records who created or revoked a key, changed a policy, or updated a setting.

Yes, via the built-in attack test. Paste your system prompt, and AiDren runs it against roughly 20 real prompt-injection and jailbreak attempts on a cheap model using your own upstream key, then shows you exactly what got through with your AiDren protection on versus off. It's included on every plan, including the trial.

Your requests pass through AiDren to make a block/allow decision and are never stored beyond the decision log you see in your own dashboard. Your API keys are encrypted at rest and never logged in plain text.

AiDren runs in the UK/EU, and your account data and decision logs stay there. If you need a dedicated deployment in another region (US, APAC) for data-residency reasons, that's available for enterprise customers — email us.

A "checked request" is one AiDren screens on its way to your model. Starter covers 100,000 a month, Growth 500,000, Scale 2,000,000. It's a fair-use guide, not a hard limit: if you go over, we email you about a 10,000-request top-up (£19) or moving up a tier, we don't cut you off mid-month. The count resets on the 1st. For very high volume, email us for a custom plan. Model-file scans and agent egress reports don't count.

AiDren fails closed. If the classification pass can't complete (the screening provider is down, a timeout, an outage) the request is blocked, not waved through. We'd rather your app get an error it can retry than silently forward an unscreened request to your model. The screening layer also runs on a primary provider with an automatic fallback, so a single provider outage doesn't take it down.

Your 14-day trial needs no card up front and covers 25,000 checked requests. When it ends, upgrade to keep your proxy running — if you don't, AiDren pauses your traffic rather than silently letting it through unprotected.

Yes, in the sense that it sits between your application and the model provider and inspects traffic in both directions. It screens prompts for injection, scans responses for secrets and personal data, and applies per-key policy. It does not replace least-privilege design for your agent's tools, which no filter can do for you.

Lakera Guard is a prompt-injection detection API, and Check Point announced its acquisition of Lakera in September 2025. AiDren also screens for injection, and adds response scanning, model-file scanning and agent egress reporting in one self-serve plan with public pricing. Lakera has a larger dedicated detection-research effort; the comparison page lists where it is ahead.

Yes. The free attack test fires six real prompt-injection and jailbreak attempts at your own system prompt with no account. The full test of about 20 attacks, with protection off versus on, is included in the 14-day trial, no card needed.

No tool does. The UK NCSC says prompt injection attacks “may never be totally mitigated in the way that SQL injection attacks can be”. AiDren blocks the attempts it recognises, logs every decision with a reason, and is designed as one layer alongside least-privilege tool access and human approval for risky actions.

AiDren is built and run by Paul Freek, a UK sole trader registered with the Information Commissioner's Office (ZCZ36167). Support is by email at [email protected].