BiVelio Shield — private prompts for ChatGPT & Claude Chrome extension security report

Keep your private data out of the AI cloud — without changing how you work. BiVelio Shield sits between you and ChatGPT or Claude and removes sensitive information from the text you type on your own machine, before a single byte leaves your browser. The AI provider receives placeholder tokens in place of those values — never the real ones — and the extension puts the real values back into the reply on screen, so your conversation reads normally. Verified end to end on both sites. On ChatGPT: a prompt carrying an email reaches the provider as a [BV:…] token, not the raw value — reload the thread and only the token was ever stored, and the reply shows your real values restored on screen. On Claude: the same round-trip was run on 2026-08-14 with a control in the same thread. IBANs, cards, national IDs and API keys run through the same engine and are covered by its test suite. What it protects (free, on-device, no signup): • Credit-card numbers (checksum-validated) • IBANs and bank details • National IDs — Spanish DNI/NIE/CIF, US SSN, and more • Emails and phone numbers • API keys & secrets — OpenAI, AWS, GitHub, Stripe, Slack, and others • IP addresses • Health, religious, biometric and genetic terms — a curated multilingual lexicon (GDPR Art. 9 special categories) Optional — "Redact on shape": turn it on to also hide mistyped IDs that fail their checksum. Off by default, and we tell you plainly it may over-redact things like order numbers or tracking codes — your choice. And even with it off: a checksum-valid identifier can occasionally swallow a word or two next to it, so the provider sees less of your sentence than you typed — never more. Honest about what it does NOT do — no dark patterns: • It does not remove people's names, addresses or general free-form text (no fixed shape to match), and an Art. 9 phrase written in wording its curated lexicon does not list will also pass. Name and context redaction is the Pro / NLP tier. • Voice / realtime mode is not protected. It redacts the text you type; a spoken turn in ChatGPT Advanced Voice or Claude voice travels over a separate live-audio connection it never sees — and a text tool cannot redact audio. Type, don't speak, when a turn carries sensitive data. • Claude's "Cowork" composer is not covered. The extension redacts Claude's normal chat send; Cowork posts to a different endpoint that it deliberately does not touch. Treat anything typed into Cowork as unprotected. • Files, images and attachments are not inspected. The engine is text-only, so an uploaded document, PDF, or a photographed passport is sent to the provider as-is. Keep sensitive data out of attachments. • Custom instructions and memory saved from the settings dialog are not redacted. Text you type in the composer is covered; text you save through ChatGPT's or Claude's own settings, memory or project-instruction screens travels on endpoints the extension does not intercept. Private by design: • 100% local on the free tier. No account, no sign-up, nothing sent to us. • Your data ↔ token map (the "vault") is stored encrypted on your device, with the key held only in memory — it is wiped when you close your browser, so old conversations de-identify themselves. • The extension only touches the ChatGPT/Claude message endpoints and never any other site. Works with: • ChatGPT (OpenAI) — verified end to end on the live site • Claude (Anthropic) — verified end to end on the live site Available on Chrome, Edge, Brave, and other Chromium browsers today. Firefox and Safari coming soon. Free. Local. Yours.