Proxia — AI firewall
Overview
Inspects your prompts (secrets, PII, injection) before sending them to an AI. Everything stays local.
Proxia is a cognitive firewall for your conversations with AI. Before you send a message to AI assistants and LLMs, Proxia scans the text on the page and warns you if it contains: secrets (API keys, tokens, passwords); personal data (email addresses, phone numbers, IBANs, identifiers); prompt injection attempts (hidden prompt manipulation). You stay in control at all times: Proxia flags potential issues and suggests a protected version of your text. It never removes or blocks anything on your behalf. You can copy the masked version, send the original anyway, or cancel. Everything stays on your device. Inspection runs locally through an embedded WebAssembly module (the same engine used by the Proxia app). No prompts, detections, or data ever leave your browser. No account, no analytics, no tracking cookies. Compatible with Chrome, Edge, Brave, Opera, and Arc.
0 out of 5No ratings
Details
- Version1.0.6
- UpdatedOctober 8, 2026
- FeaturesOffers in-app purchases
- Offered byguillaume.magery
- Size1.2MiB
- Languages3 languages
- DeveloperFabindias
rue de linthout, 107 Bruxelles 1200 BEEmail
contact@tametrust.comPhone
+32 493 18 35 78 - TraderThis developer has identified itself as a trader per the definition from the European Union and committed to only offer products or services that comply with EU laws.
- D-U-N-S371854744
Privacy
This developer declares that your data is
- Not being sold to third parties, outside of the approved use cases
- Not being used or transferred for purposes that are unrelated to the item's core functionality
- Not being used or transferred to determine creditworthiness or for lending purposes
Support
For help with questions, suggestions, or problems, please open this page on your desktop browser