# ContextHound

> Real-time prompt injection scanner. Detect injection attacks before they reach your AI model.

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

## Overview

- **ID:** `contexthound`
- **Platform:** Firefox
- **Type:** Firefox add-on
- **Status:** Available
- **Publisher:** IulianVOStrut
- **Category:** privacy-security
- **Daily users:** 1
- **Weekly downloads:** 1
- **Version:** 1.9.0
- **Last updated:** 2026-03-18
- **First published:** 2026-03-15
- **Size:** 100 KB
- **Data as of:** 2026-09-06
- **Store listing:** [Firefox Add-ons Store](https://addons.mozilla.org/firefox/addon/contexthound/)
- **Website:** [https://contexthound.com/privacy](https://contexthound.com/privacy)
- **Privacy policy:** [https://addons.mozilla.org/firefox/addon/contexthound/privacy/](https://addons.mozilla.org/firefox/addon/contexthound/privacy/)

## Description

ContextHound scans text you type into AI tools for <strong>prompt injection attacks</strong> - attempts by malicious content to hijack, manipulate, or jailbreak the AI model you are using.

<strong>Scan pill</strong>
A lightweight indicator appears next to any AI chat input on any website. As you type, ContextHound analyses the text against 70+ detection rules covering jailbreaks, role-hijack instructions, indirect injection, data exfiltration attempts, system-prompt overrides, and more. A risk score and plain-English explanation appear instantly.

<strong>DevTools panel</strong>
Open the browser DevTools and select the ContextHound tab to monitor live LLM API traffic. The panel intercepts and scans requests to OpenAI, Anthropic, Google Gemini, Mistral, Groq, Cohere, DeepSeek, and others.

<strong>Popup scanner</strong>
Click the toolbar icon to paste and scan any text manually before sharing it with a model.

<strong>Privacy</strong>
Everything runs entirely in your browser. No text, prompt content, scan results, or metadata is collected, stored externally, or transmitted anywhere. The extension has no backend server. Full source code is available on GitHub.

## Rankings

- #100,759 — Overall
- #250 — context menu

## Permissions and access

### Permissions

- `storage`
- `webRequest`

### Host permissions

- `<all_urls>`

### Content script matches

- `<all_urls>`

## Safety

- **Risk impact:** High risk impact
- **Risk likelihood:** Moderate risk likelihood

### Analysis details

- Allows access to all websites, posing a significant security risk as it can monitor and modify data from any visited site.
- 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-injection-detector](https://chrome-stats.com/d/prompt-injection-detector)
- [PromptVigil](https://chrome-stats.com/d/promptvigil)
- [AI Prompt Injector](https://chrome-stats.com/d/ai-prompt-injector) — 6 users, 5.00 / 5
- [Prompt Leak Guard](https://chrome-stats.com/d/prompt-leak-guard)
- [CleanMyPrompt - AI Privacy Firewall](https://chrome-stats.com/d/cleanmyprompt-ai-firewall)
- [Prompt Guard](https://chrome-stats.com/d/prompt-guard) — 1 users
- [PromptSync PRO](https://chrome-stats.com/d/promptsync-pro) — 1 users, 5.00 / 5
- [Prompt Armour — AI Privacy Guard](https://chrome-stats.com/d/prompt-armour-ai-privacy-guard) — 1 users
- [Prompt Injector for ai tools](https://chrome-stats.com/d/prompt-injector-for-ai-tools) — 6 users
- [BlackStone Prompt Manager](https://chrome-stats.com/d/blackstone-prompt-manager) — 1 users
- [AI Prompts](https://chrome-stats.com/d/ai-prompts) — 1 users
- [InsightPilot - Context-Aware AI](https://chrome-stats.com/d/insightpilot-context-aware)

---

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