// built for the skeptic

Don't trust our privacy claim. Verify it.

MoorAI inspects AI prompts, files, and outputs for risk without the content ever leaving the device. That's not a policy we promise — it's how the agent is built, and the agent is open source, so you can confirm it line by line.

Content-free by construction — and you can verify it

Most “privacy-first” AI security tools ask you to trust a data-handling policy. MoorAI removes the need for trust by removing the data from the equation. Every detection runs locally, on the endpoint. Before anything is evaluated, content is reduced to one-way hashes (djb2 for fast fingerprint matching, SHA-256 where collision resistance matters). A hash is a fingerprint, not the thing itself — there is no key, no reverse function, no server-side decode, because the plaintext was never sent anywhere to decode.

The console receives verdicts and metadata — what class of risk fired, when, on which device, mapped to which framework. It never receives the text that produced the verdict. And because the on-device agent is licensed AGPL-3.0, you don't take our word for it: read the source, run the agent under a network monitor, and confirm no content egresses. The license makes independent verification a right, not a favor.

Leaves the device — verdicts + metadata	Never leaves the device
Risk classification (e.g. OWASP LLM01 match)	Prompt text
One-way hashes used for matching	File contents
Detection timestamp	Model output / responses
Device & policy identifiers	Any reconstructable plaintext
Severity & rule id	Decryption keys (there are none to send)

The mechanism is the guarantee: you cannot leak what you never transmit. Verify it in the source, then confirm it on the wire.

Capture tiers — the honest exception

There is exactly one way content is ever retained, and we state it plainly rather than bury it. An administrator can enable a capture tier — for incident investigation or compliance evidence. It is fenced accordingly:

• Off by default. Out of the box, MoorAI is fully content-free — no capture, no exceptions.
• Admin-gated. Only an administrator can enable it — not the agent, not a policy push you didn't author, not an end user.
• Logged. Enabling capture is itself an audited event: who turned it on, when, for which scope.
• Tier-limited. Scoped by tier, not all-or-nothing — enable the minimum needed, not a firehose.

If you never enable a capture tier, MoorAI never stores content. Full stop.

Detection efficacy — measured, and reproducible

A privacy guarantee is worthless if the tool can't catch anything. MoorAI ships an on-device benchmark that exercises the detection engine against a labeled corpus — including an adversarial red-team set — and reports precision and recall per threat class, mapped to the OWASP LLM Top 10 and MITRE ATLAS. Run it yourself:

npm run benchmark

Results are written to docs/BENCHMARK.md. Because it runs locally against the shipped detection logic, the numbers you produce are the numbers we publish — no hidden test set, no vendor-tuned demo. Current adversarial red-team coverage: 97 / 97 cases caught.

Trust roadmap — what we're committing to next

We won't claim assurances we don't have. Two independent validations are planned; here's exactly what each will prove, and its honest status.

• Third-party zero-egress audit — planned. An external firm will independently verify that the on-device agent transmits no prompt, file, or output content. Because the agent is AGPL-3.0, the auditor works from the same source you can read. Status: planned, not yet started — we'll publish the report and scope when it completes.
• SOC 2 Type II (console) — in progress. The proprietary console is pursuing SOC 2 Type II covering security, availability, and confidentiality of the backend that receives verdicts and metadata. Status: in progress; report not yet issued. We won't call MoorAI “SOC 2 certified” until an auditor issues the report.

Honest status matters more than a badge. The content-free mechanism and the reproducible benchmark are available today; the audit and SOC 2 are commitments in flight.