A new browser extension has been developed to solve the growing problem of sensitive data leaking into AI chat services through everyday work tasks.
HR specialists, lawyers, accountants, and IT staff routinely paste resumes, contracts, payroll tables, and configuration files containing personal data, bank details, and passwords directly into AI prompts. Once sent, this information remains on third-party servers with no reliable way to delete it from logs or training datasets.
The extension intercepts messages and file uploads at the moment of sending, replaces detected sensitive values with unique pseudonyms such as [user_qhb6tm] or [card_348zsg], and forwards only the masked text to the AI. When the AI replies using the same placeholders, the extension instantly restores the original values on the user's screen while the server sees only the anonymized version.
Earlier approaches proved insufficient. Manual replacement quickly failed due to user fatigue. Simple regex scripts struggled with Russian grammar, false positives on invoice numbers, and inconsistent name formats. External anonymization services merely shifted the trust problem to another third party.
The final solution meets three strict requirements: fully automatic operation without user intervention, completely local processing with no internet required after installation, and seamless integration that does not change how people interact with their preferred AI chat interface.
Inside the engine, 33 data categories are defined declaratively with patterns, validators, and priorities. INN numbers are verified using FNS checksum algorithms, cards use the Luhn check, and passwords are filtered by entropy and stop-word lists. Russian names are normalized to nominative case so that declined forms receive the same pseudonym. The response parser tolerates case changes, spaces, markdown, and homoglyphs to ensure reliable decoding even when models alter labels.
File support includes more than 70 formats. Office documents are processed by creating anonymized copies that preserve formatting, tables, and headers. Scanned PDFs and photos are handled by a local offline OCR engine that runs in a single worker thread, keeping memory usage low and the system responsive.
A free version covering all text categories and custom rules is available in the Chrome Web Store. Advanced features for files, scans, and enterprise policy distribution are provided upon request.
