# Red-team your robot policy before a pilot - Provael

> Markdown twin of https://www.provael.com/for/robotics-startups/ - derived mechanically from the page's own rendered content at
> build time (it can state nothing the page does not). Curated, data-driven twins exist for the
> key pages; this one is generated so the twin convention has no holes.

FOR ROBOTICS STARTUPS

# Red-team your robot policy before a pilot.

Before a pilot customer relies on it, find out how often an unusual instruction pushes your policy out of its safe zone. Provael tests it in simulation, beside a harmless control. The tool is free; the fixed-price Checkpoint Report adds a reproducible report and an engineering review.

Every attack family · free Defensive · sim-only CPU-first · Apache-2.0

## Who this is for

You are a small team shipping a learned robot policy. The next thing between you and a deployment is often a document: a customer’s security questionnaire, a CE technical file, an insurer’s application or a diligence list. None of them asks a settled question about learned robot policies yet. A measurement anyone can re-run gives you something to hand over.

## What applies to you, and when

EU Machinery Regulation 2023/1230 - Annex III 1.1.9 and 1.2.120 January 2027: If you sell into the EU, the machine your policy drives must meet the Annex III requirements that apply to it, 1.1.9 and 1.2.1 among them, from this date: protection against corruption and resistance to malicious attempts. The technical file carries the evidence. The delegated acts adding the AI Act robustness requirements apply by 2 August 2028; until then the evidence is your own.

Product Liability Directive (EU) 2024/28539 December 2026: Software and AI systems are products. After this date defectiveness may be presumed where relevant evidence is not disclosed, which is a reason to have a dated measurement before you are asked.

The customer’s security questionnaire: It often arrives before any regulation does. Provael publishes its own answers, the questions it answers "No" included, and the same shape works for your answers about the policy. [Provael’s answers →](https://www.provael.com/trust/)

## What you get

- The report and its SARIF file: the attack-success rate (how often the policy left its safe zone) with 95% confidence intervals, the benign and clean-task-success controls, and the release decision under your acceptance protocol.
- The GitHub Action that fails your CI build when that decision is a fail.
- The signed attestation over the whole pack, which you verify offline.
- The technical-file annex: the test report in the ISO/IEC 17025 clause-7.8 shape (not accredited, no statement of conformity) and the crosswalk.
- Or run the same measurement yourself, free: pip install provael, run the full sweep on the CPU stub in about twenty seconds, then your own checkpoint on a GPU with the committed recipe. [Run the quickstart →](https://www.provael.com/quickstart/)

The [sample evidence pack](https://www.provael.com/sample-evidence-pack/) is a real pack from the committed run, published in full. The one measured result, and what it does not mean, is on [the results page](https://www.provael.com/results/).

## Start with one checkpoint

The Checkpoint Report covers one eligible checkpoint at a fixed price; for more, start with a scoping call. Eligibility is confirmed by a short form and a human reply before anything is sent or paid.

[Check eligibility →](https://www.provael.com/checkpoint-report/#eligibility) Book a scoping call

Feature and status claims on this page were read against the product repository on 20 September 2026. This page was rewritten on 1 November 2026, after that check; the re-check is pending. Unlike the numbers on [/results](https://www.provael.com/results/) and [/leaderboard](https://www.provael.com/leaderboard/), these claims are not enforced by a build check: this is a human review with a date on it, not a guarantee. The maintained source is [the repository](https://github.com/provael/provael); where it disagrees with this page, it wins.

---
Canonical: https://www.provael.com/for/robotics-startups/