VaultSnip privacy policy
Short version: VaultSnip stores nothing about you or your images.
- No accounts, no backend, no database. VaultSnip is static code that runs in your browser.
- Your images stay on your device. Text recognition (OCR), masking and the safety check run locally in your browser. Images and results are held in memory and disappear when you close the tab.
- What leaves your device. Only when you click send, and only the masked image you approved, goes directly from your browser to the AI provider you chose, Anthropic (Claude) or OpenAI, using your own API key. It never passes through a VaultSnip server. That provider's API terms and data policy apply to the request.
- Samples send nothing at all.
- What your browser keeps. The OCR language model (an app file, cached so it downloads once) and, only if you tick "remember", your API key, its provider and the model name. You can remove them at any time from "AI key" → "Forget key". "Check key" asks the provider which models the key can use; it sends only the key.
- Extension permissions.
activeTabonly: the extension can capture the tab you are on, and only when you click its icon. - Exports are files saved to your computer. They contain generated data, a watermark and a link to VaultSnip. They make no network calls by themselves.
- Feedback is your choice. The Feedback button prepares a report (VaultSnip version, browser, the step you were on, chart types and any error message, never your screenshot or dashboard text). Nothing is sent until you choose to continue on GitHub, where it is posted under your GitHub account, or to email it from your own mail app. GitHub's or your email provider's terms apply.
- No analytics, cookies or tracking.
Last updated: 7 October 2026.
Contact: use Feedback in the app, or the GitHub repository. Security concerns: report privately.