Software decision profile

Lakera Guard

A real-time API that inspects prompts and model output for prompt injection, jailbreaks, system-prompt extraction and PII leakage, sitting between your application and any LLM.

CybersecurityLakera GuardDecision profile Fathom Layer

Evidence statusSpecs not independently verifieddocs.lakera.ai

Visit site

Editorial assessment freemium

Explore the trade-offs.

Where it stands outModel-agnostic — sits in front of hosted APIs or local models alikeExplore strengths ↗Close details ↑

Covers direct and indirect prompt injection, jailbreaks, system-prompt extraction and PII leakage
Filters are updated from a large, real-world attack dataset (Gandalf)

What to weighClosed-source commercial service — an external dependency on the request pathExplore limitations ↗Close details ↑

Detection-based: a high block rate is not a guarantee
Headline accuracy and latency numbers are vendor-published, not independently measured

Best suited toTeams shipping LLM features to production without an in-house security team · Agent and RAG pipelines exposed to untrusted input · Organisations already standardised on Check Point

Read at the source

What Lakera Guard’s own pages state.

Each line was read on the vendor’s site and found word for word in the quoted page. It records what the vendor states, not a test by Fathom Layer.

Deployment: AI Guardrails is available as an enterprise grade Software as a Service (SaaS) cloud-hosted solution or Self-hosted product.docs.lakera.ai Checked automatically · Sep 16, 2026

Where it wins, where it doesn't

Pros

Model-agnostic — sits in front of hosted APIs or local models alike
Covers direct and indirect prompt injection, jailbreaks, system-prompt extraction and PII leakage
Filters are updated from a large, real-world attack dataset (Gandalf)

Cons

Closed-source commercial service — an external dependency on the request path
Detection-based: a high block rate is not a guarantee
Headline accuracy and latency numbers are vendor-published, not independently measured

Ideal forTeams shipping LLM features to production without an in-house security teamAgent and RAG pipelines exposed to untrusted inputOrganisations already standardised on Check Point

Key Features

✦Real-time request and response scanning
✦Single chat-completions-style API endpoint
✦Prompt injection and jailbreak detection
✦PII and data-leakage detection
✦Self-hosted deployment option

Editorial note

Lakera Guard is a detection layer, not a guarantee. It scores every request in and every response out, blocks what crosses a threshold, and is model-agnostic — it works whether the model runs on a hosted API or on your own hardware. Its filters are trained partly on data from Gandalf, Lakera's public prompt-injection game, which has collected millions of real attack attempts. Check Point acquired Lakera in 2025 (reported around $300 million); the product now also ships as Check Point AI Guardrails, while the standalone Guard API and its free tier still exist. The detection-rate, latency and language-count figures Lakera publishes (98%+, sub-50ms, 100+ languages) are the vendor's own — treat them as a claim, not a measured result. The real trade-off is architectural: you add a network hop and an external dependency to every LLM call, in exchange for a maintained, continuously updated filter you do not have to build or keep current yourself.

Frequently Asked Questions

Who is Lakera Guard for?↓

Lakera Guard is a fit for teams shipping LLM features to production without an in-house security team, Agent and RAG pipelines exposed to untrusted input and Organisations already standardised on Check Point.

What are the drawbacks of Lakera Guard?↓

The trade-offs we record are: Closed-source commercial service — an external dependency on the request path, Detection-based: a high block rate is not a guarantee and Headline accuracy and latency numbers are vendor-published, not independently measured.

What does Lakera Guard do well?↓

Model-agnostic — sits in front of hosted APIs or local models alike, Covers direct and indirect prompt injection, jailbreaks, system-prompt extraction and PII leakage and Filters are updated from a large, real-world attack dataset (Gandalf).

Alternatives to consider

See all alternatives →

Continue the inquiry