prompt-injection-detector

Name: prompt-injection-detector
Author: Vishesh Agarwal

By: Vishesh Agarwal Add-on

Detects hidden prompt injection instructions that might manipulate AI models like Copilot and Claude.

Overview

Firefox Add-ons Store

Daily users

Data as of 2026-07-15

Version:

1.0.0

Last updated: 2026-04-07

Features & Capabilities

AI assistants like GitHub Copilot, ChatGPT, and others read web page content when you ask them to help. Attackers can hide malicious instructions in that content — invisible to you, but visible to the AI — to hijack its behaviour, steal your data, or bypass safety filters.

PromptGuard detects:

Hidden elements (display:none, visibility:hidden, zero opacity, sub-pixel fonts, same-colour text)
HTML comments — invisible to humans but read by AI tools ingesting page source
LLM-specific formats: [INST], system:, assistant: prompt injection patterns

Three sensitivity levels:

🟢 Normal — high-confidence imperative overrides only (low false positives)
🟠 High — adds jailbreak, DAN, developer-mode, bypass patterns
🔴 Ultra — adds roleplay, persona, exfiltration, and LLM prompt-format patterns

Click any finding to flash and scroll to the exact element on the page.

All scanning runs locally in your browser. Nothing is sent anywhere.

User Growth & Download Statistics

Add-on

By:

Vishesh Agarwal

Daily users:

Version:

1.0.0 Last updated: 2026-04-07

Version code:

6208187

Creation date:

2026-04-04

Risk:

Permissions:

Host permissions:

http://*/*
https://*/*

Size:

20.48KB

Email:

cy*****@gmail.com

URLs:

Full description:

Source:

Firefox Add-ons Store

Data ingested on:

2026-07-15

Compare stats and ranking:

Ranking

# 145,126 ▼ 27,834

Other rankings

#104 in inject keyword 14 ▼ 53#216 in prompt keyword 16 ▼ 94

For Developers

Monetize with App Pass Boost with Extension Booster

Contact the developer

Chrome-Stats does not own this Firefox add-on. Please use these information below to contact the Firefox add-on developer.

Developed by:

Vishesh Agarwal

Firefox Add-ons Store

https://addons.mozilla.org/firefox/addon/prompt-injection-detector/

Email:

cy*****@gmail.com

Is prompt-injection-detector Safe?

Risk impact

Risk impact measures the level of extra permissions an extension has access to. A low risk impact extension cannot do much harms, whereas a high risk impact extension can do a lot of damage like stealing your password, bypassing your security settings, and accessing your personal data. High risk impact extensions are not necessarily malicious. However, if they do turn malicious, they can be very harmful.

prompt-injection-detector requires a few sensitive permissions. Exercise caution before installing.

Risk impact analysis details

Critical Allows access to all websites, posing a significant security risk as it can monitor and modify data from any visited site.

Risk likelihood

Risk likelihood measures the probability that a Firefox add-on may turn malicious. This is determined by the publisher and the Firefox add-on reputation on Firefox Add-ons Store, the amount of time the Firefox add-on has been around, and other signals about the Firefox add-on. Our algorithms are not perfect, and are subject to change as we discover new ways to detect malicious extensions. We recommend that you always exercise caution when installing a Firefox add-on.

prompt-injection-detector may not be trust-worthy. Avoid installing if possible unless you really trust this publisher.

Risk likelihood analysis details

High This extension has low user count. Unpopular extensions may not be stable or safe.
Medium **** ********* *** ***** ** *** **** * ******* *** ********** *** *** ** ****** ** *****
Low **** ********* *** ******* **** **** * ****** **** ***** ******** *** **** ****** ** ** ****** *** *****