# SafePrompt

> SafePrompt — protection des donnees sensibles dans vos prompts LLM (100% local)

Canonical page: [https://chrome-stats.com/d/safeprompt](https://chrome-stats.com/d/safeprompt)

## Overview

- **ID:** `safeprompt`
- **Platform:** Firefox
- **Type:** Firefox add-on
- **Status:** Available
- **Publisher:** SafePrompt
- **Category:** web-development,privacy-security
- **Rating:** 5.00 / 5 (1 ratings)
- **Version:** 0.1.4
- **Last updated:** 2026-05-28
- **First published:** 2026-05-20
- **Size:** 1.86 MB
- **Data as of:** 2026-09-10
- **Store listing:** [Firefox Add-ons Store](https://addons.mozilla.org/firefox/addon/safeprompt/)
- **Website:** [https://safeprompt.m-kis.fr/fr/support](https://safeprompt.m-kis.fr/fr/support)
- **Privacy policy:** [https://addons.mozilla.org/firefox/addon/safeprompt/privacy/](https://addons.mozilla.org/firefox/addon/safeprompt/privacy/)

## Description

SafePrompt protects your sensitive data before it reaches ChatGPT, Claude, Gemini, DeepSeek, Qwen, OpenRouter, and Mistral Le Chat.

100% LOCAL — NO DATA LEAVES YOUR BROWSER

All processing (detection, tokenization, rehydration) happens inside your browser. SafePrompt never sends your prompts to a third-party server. GDPR-compliant by design.

AUTOMATIC DETECTION AND MASKING

Before your prompt is sent, SafePrompt detects:
- Secrets: API keys (AWS, GitHub, Stripe, OpenAI), JWT tokens, plaintext passwords
- Personal identifiers: email, phone, IBAN, credit card number
- French identifiers: SIRET, SIREN, social security number (NIR), VAT number
- Postal addresses, dates of birth

Secrets are blocked (fail-closed); personal data is automatically replaced with tokens (⟦EMAIL_1⟧, ⟦FR_SIREN_2⟧, etc.) before sending.

TRANSPARENT REHYDRATION

When the LLM replies with the tokens, SafePrompt restores the original values — only inside your browser. Hover a restored token → tooltip confirms "SafePrompt restored this value locally". The LLM never saw the original data.

7 SUPPORTED PLATFORMS
<ul><li>ChatGPT (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/68a188960f04e2a84c1f04ab562a849360a490d4e86c75e7c7be3ab59437f37d/http%3A//chatgpt.com" rel="nofollow">chatgpt.com</a>)</li><li>Claude (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/749f55679c25c240feed4c33d337c9a6fd364a96bdf82dafdc769bc8883d8fcd/http%3A//claude.ai" rel="nofollow">claude.ai</a>)</li><li>Gemini (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/187ed18c48fe4e37708681edcdd7edf8bc86c3385debd75875ddac265b398f10/http%3A//gemini.google.com" rel="nofollow">gemini.google.com</a>)</li><li>Qwen (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/c71cbaf69f51ba295d0859371e9d894a2c15892bf24cb75e2a2742be42113ae0/http%3A//chat.qwen.ai" rel="nofollow">chat.qwen.ai</a>)</li><li>DeepSeek (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/1783738123526d6031c48592a820f5af2f46c9578f27cf824241e90d8b3ba6db/http%3A//chat.deepseek.com" rel="nofollow">chat.deepseek.com</a>)</li><li>OpenRouter (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/236b75c310df32459252224495f7caf884fd089903b451467b534a3b596c749e/http%3A//openrouter.ai" rel="nofollow">openrouter.ai</a>)</li><li>Mistral Le Chat (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/60995438d3e68e237f6a7d6a74051115010246d9619e81bfabcac9e661ad422b/http%3A//chat.mistral.ai" rel="nofollow">chat.mistral.ai</a>)</li></ul>
TEAM DASHBOARD

Solo Paid, Starter, and Business plans include a centralized dashboard on <a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/3c11596ee6d1dee14fa21dae7bbdd71c633e9516116b3660633dae64c7e15d8e/http%3A//safeprompt.m-kis.fr" rel="nofollow">safeprompt.m-kis.fr</a>: incident visibility, seat management, audit log, per-tenant anonymization (SHA256 + salt), GDPR export.

PLANS
<ul><li>Solo Free — free, secrets detection only</li><li>Solo Paid — €5/month, full secrets + PII detection</li><li>Starter — €12/seat/month (5–49 seats), team dashboard</li><li>Business — €8/seat/month (50+ seats), anonymization, priority support</li></ul>
SECURITY AND COMPLIANCE
<ul><li>No "&lt;all_urls&gt;" permission — host_permissions limited to the 7 supported LLMs</li><li>GDPR by default: no personal data sent to third parties</li><li>Manifest V3 compliant, regular dependency audits</li></ul>
SafePrompt is published by M-KIS (<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/148492a17d1997cb5cdfb9bb572b174615ca451781dd1f26cf6f1e88482b7a84/https%3A//m-kis.fr" rel="nofollow">https://m-kis.fr</a>), a Lorraine-based agency specialized in cybersecurity and responsible AI.

Support &amp; questions: contact@m<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/13c4c63aa3d47ff8d73c41c14c03e0ee92cbd560ef3c1fc1aa76ca29d220250d/http%3A//-kis.fr" rel="nofollow">-kis.fr</a>

## Rankings

- #130,393 — Overall

## Permissions and access

### Permissions

- `activeTab`
- `storage`
- `alarms`
- `identity`

### Host permissions

- `https://chatgpt.com/*`
- `https://claude.ai/*`
- `https://gemini.google.com/*`
- `https://chat.qwen.ai/*`
- `https://chat.deepseek.com/*`
- `https://openrouter.ai/*`
- `https://chat.mistral.ai/*`
- `https://*.sentry.io/*`
- `https://*.ingest.sentry.io/*`

### Content script matches

- `chatgpt.com`
- `claude.ai`
- `gemini.google.com`
- `chat.qwen.ai`
- `chat.deepseek.com`
- `openrouter.ai`
- `chat.mistral.ai`

## Safety

- **Risk impact:** Very high risk impact
- **Risk likelihood:** Moderate risk likelihood

### Analysis details

- Request access to the following domains: chatgpt.com, claude.ai, google.com, qwen.ai, deepseek.com, openrouter.ai, mistral.ai, sentry.io
- This extension has low user count. Unpopular extensions may not be stable or safe.

> Some risk analysis details are omitted from this free response. [Upgrade to view the full analysis](https://chrome-stats.com/pricing).

## Similar extensions and apps

- [Prompt Guard](https://chrome-stats.com/d/prompt-guard) — 1 users
- [Prompt Leak Guard](https://chrome-stats.com/d/prompt-leak-guard)
- [CleanMyPrompt - AI Privacy Firewall](https://chrome-stats.com/d/cleanmyprompt-ai-firewall)
- [Private Prompt - AI Privacy Shield](https://chrome-stats.com/d/private-prompt-privacy-shield) — 1 users
- [PromptMate](https://chrome-stats.com/d/promptmate) — 1 users
- [TeamPrompt AI Prompt Manager](https://chrome-stats.com/d/teamprompt-ai-prompt-manager) — 1 users
- [PromptProtect](https://chrome-stats.com/d/promptprotect)
- [PromptVigil](https://chrome-stats.com/d/promptvigil)
- [TeamPrompt — Manage & Shield](https://chrome-stats.com/d/teamprompt-manage-shield) — 3 users, 5.00 / 5
- [Pingbird Prompt Compressor](https://chrome-stats.com/d/pingbird-prompt-compressor)
- [Promptrix](https://chrome-stats.com/d/promptrix) — 1 users
- [Promptory](https://chrome-stats.com/d/promptory) — 8 users

---

Source: [Chrome-Stats](https://chrome-stats.com/d/safeprompt)