Lakera Guard (Check Point AI Guardrails) by Check Point

# Fix list: Lakera Guard (Check Point AI Guardrails)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/lakera-guard, the October 2026 research run, assessed 1 October 2026. Grade C, 59.7 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Lakera Guard (Check Point AI Guardrails): work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Payments & pricing, 15 out of 100, up to 10.6 more on the total

Why it scored 15: No x402, MPP or L402 (0). The Community limit of 10,000 requests a month is public, but there's no price above it, and Enterprise is by sales (5 of 20, our call for a published free plan with no prices). Community is self-serve, and last week's check found no card step, which we couldn't repeat today (10 of 20). A person signs up on platform.lakera.ai and makes the key (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 2. Reliability, 65 out of 100, up to 7 more on the total

Why it scored 65: status.checkpoint.com lists Check Point AI Security (Lakera Guard) with platform, EU API and APAC/US API components (20). Its incident feed from 1 July to 30 September 2026 has 18 entries, all for other Check Point products, so nothing for the Guard API (30). No rate-limit numbers published for Community or Enterprise (0). The API reference lists 429 Too many requests, with no Retry-After or backoff guidance (5 of 15). No SLA found (0). /v2/guard is GA (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Maintenance & community, 21 out of 100, up to 6.9 more on the total

Why it scored 21: Last changelog entry on 8 June 2026, Enhanced Breakdown Response, about 115 days ago (10). No dated entries since 3 July (0). Public changelog and Check Point support, no public issue tracker (8 of 15). No official SDK packages (0). Self-hosted container releases on the stable tag every few weeks until 2.0.493 on 2 April 2026 (3 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 4. Security & auth, 65 out of 100, up to 6.1 more on the total

Why it scored 65: Bearer API keys made on the dashboard, with no scopes, expiry or rotation documented (20 of 30). Dashboard roles are User, Admin and No access, but a key can't be limited further (10 of 20). The service is a prompt-attack detector that also screens tool calls and tool results in the same request (15). Every screening request is logged with its prompt and output in the dashboard by default, and logs can be exported to S3 for a SIEM (15). SOC 2 Type II and ISO 27001:2022 on the trust centre, but no security.txt on lakera.ai or checkpoint.com, no disclosure policy or bug bounty found, and no advisories (5 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 5. Agent ergonomics, 77 out of 100, up to 3.7 more on the total

Why it scored 77: The default response is flagged plus a request id, and breakdown, payload and dev_info add detail only when asked (25). The project's policy picks the detectors, and the three flags size each response (20). Four status codes with short descriptions (12 of 20). A screen has no side effect beyond logging, but there's no retry guidance, and every call is stored for the dashboard by default (12 of 20). OpenAI message format in, no official SDK packages (8 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 6. Transparency & trust, 59 out of 100, up to 3.6 more on the total

Made of editorial 43, provenance 75.

Why it scored 59: Closed service, but the footer terms now point at a Check Point page we couldn't read without JavaScript, so the contracting entity is unclear (10 of 30). Prompts and outputs are stored for the dashboard by default and admins can switch it off, retention controls are Enterprise-only, the trust centre says data is deleted on request, and no retention period is published for Community (15 of 30). No deprecation policy or dated notices found (0). Storage region fixed at organisation creation (EU by default), regional EU, US and Singapore hosts, and a sub-processor list on checkpoint.com (18 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: lakera.ai, no registry record we could read (0 of 15)
- security.txt: not found (0 of 10)

## 7. Schema & documentation, 86 out of 100, up to 2.3 more on the total

Why it scored 86: docs.lakera.ai/openapi.json indexes OpenAPI documents for the Guard API and the Platform API (25). llms.txt and a .md version of each page (10). The guide says what's screened (the last interaction), how Detect and Enforce differ, and recommends a calibration cycle before enforcing (16 of 20). role is an enum of five values and the flags are booleans, but "messages required unless tools" is stated in prose rather than the schema (12 of 15). Request examples in the docs, and 400, 401, 429 and 500 documented with one-line descriptions (10 of 15). Versioned path (/v2) and a dated changelog, quiet since 8 June 2026 (13 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Whether Community sign-up asks for a card. Last week's check found no card step, and we couldn't repeat it today.
- Community rate limits and the per-request size limit outside Enterprise.
- How long Community prompts and outputs are kept when dashboard logging is on.
- Which Check Point entity contracts for the service, since the terms page needs JavaScript.

## Weaknesses

- Prompts and outputs are stored for the dashboard by default
- No public pricing above the free tier and no published rate limits
- Only the last interaction is screened, so a slow multi-turn attack needs your own history handling
- No official SDK packages
- Changelog quiet since 8 June 2026, and no security.txt or disclosure policy found

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Start the project in Detect mode and calibrate before Enforce. In Detect mode flagged is always false
- Send the whole conversation, but expect only the last user, assistant or tool turn to be scored
- Ask for breakdown=true and treat the confidence levels as a dial, not a boolean
- Turn off prompt logging in General Settings if the dashboard shouldn't hold user content
- Pin eu.api.lakera.ai or us.api.lakera.ai rather than api.lakera.ai when residency matters

## What the review panel asked for

- Put the messages-or-tools rule in the schema
- Publish rate limits and Retry-After
- a published Community retention period
- expiring scoped keys

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.