Skip to content
Ask Claude about any Chrome extension, answered with Ext Watch data. See how →
Tools extension

PromptGuard

  • 3 users
  • No ratings yet
  • #111,246in Tools

Flags likely prompt-injection text as you type in ChatGPT, Claude and Gemini, using your own PromptGuard API.

by arshitha7349 · 1 listing

Add to RadarChrome Web Store Free plan tracks 1 extension · no card
extwatch.com/extensions/promptguard-pmfjmeoadommikmegdndgejklpgjpfbc
PromptGuardarshitha7349 · ToolsLow access
Users
3
#111,246 of 119,276 in category
Rating
—
No ratings yet · median 4.59
Version
1.1.0
14.52 KiB · Manifest V3
Access
Low5/100
1 permission + 1 site pattern
From the store listing

Screenshots

5 images from the publisher · use the arrows or pick one · swipe or pick one

PromptGuard screenshot 1PromptGuard screenshot 2PromptGuard screenshot 3PromptGuard screenshot 4PromptGuard screenshot 5
1 / 5

Description

As written by the publisher on the store

PromptGuard checks what you type into AI chat prompt boxes for prompt-injection and jailbreak patterns, such as "ignore all previous instructions" or attempts to reveal a system prompt, and shows a small badge next to the box: Safe, Review or Danger. A Danger badge also lists the patterns that matched.

  • How it works:
  • You connect the extension to a PromptGuard API endpoint and enter an API key on the Settings page. The API is open source; you can run your own or use one you have been given access to.
  • While the extension is enabled and configured, the text in the prompt box is sent to that endpoint only, and the result is shown as a badge. Nothing is sent anywhere else.
  • Choose between three models: classical (fast, default), bert (DistilBERT) and guard (ModernBERT), if your server has them loaded.
  • Turn checking on or off at any time from the toolbar popup.

Works on chatgpt.com, chat.openai.com, claude.ai and gemini.google.com.

Privacy: your API key is stored only on your device. The extension contains no analytics, no ads and no remote code.

Limitations: detection is statistical and can be wrong in both directions; treat the badge as a hint, not a guarantee. English only.

PromptGuard is an independent open-source project and is not affiliated with, endorsed by or sponsored by OpenAI, Anthropic or Google.

Source code: https://github.com/Arshu-1104/AI-Prompt-Injection

Ratings and reviews

Ratings as the store shows them
Reviews on the store
—No ratings yet

No written reviews held for this listing yet.

Radar

Track PromptGuard on Radar

This page shows the listing as it is today. Add it to Radar and get one email when it changes.

  • Users and rating
  • Store text and screenshots
  • Permissions it asks for
Free plan tracks 1 extension · no card
Ext Watch Radar watchlist cards showing tracked extensions with users, rating, version and latest store change
Guide

PromptGuard, in plain words

What it is, what to use instead, what it can access and how to fix it.

At a glance

PromptGuard at a glance

PromptGuard is a Tools extension by arshitha7349 with 3 users. It has no store ratings yet, so there is little public feedback to go on. By users it sits in the lower half of Tools extensions.

By users
#111,246of 119,276 in Tools
Access
Low5 of 100

PromptGuard alternatives

Closest by what they do · users as the store shows them · bars on a log scale
PromptGuard3no rating
PromptStorm - ChatGPT, Gemini, Claude Prompts20K3.2 ★AI Prompt Generator & Optimizer for ChatGPT, Claude, Gemini - Feedough1K5.0 ★Prompt Library Manager1K5.0 ★TresPrompt: AI Prompt Optimizer for ChatGPT, Claude & Gemini3605.0 ★Promptly: AI Prompt Manager for ChatGPT, Claude & Gemini3095.0 ★
Permissions

Is PromptGuard safe?

PromptGuard asks for 1 permission and access to 1 site pattern. None of them are on our list of wide-access permissions.

Permissions show what it could do, not what it does. See the full permission list.

5/ 100Low access
PromptGuard1 permission
  • storageNot on our wide-access list

Every permission PromptGuard asks for

1 permission + 1 site pattern · none sensitive · Low access overall

Sites

  • Read and change data on matching siteshttps://ai-prompt-injection.onrender.com/*

Browser permissions · 1

  • Save its own settingsstorage

Sensitive marks access that reaches your data or other sites. The access level is a 0 to 100 score of all of it: under 25 is Low, 60 and up is High.

Troubleshooting

PromptGuard not working?

What recent reviews say

Store reviews from the last 90 days

We have no recent public signals of problems with PromptGuard.

Common fixes

Try them in this order
  1. 1Update Chrome and the extension
  2. 2Turn it off and on in chrome://extensions
  3. 3Reload the page
  4. 4Turn other extensions off in case two clash

Still stuck? Contact the maker or try an alternative.

300K Chrome extensions in one place

Know when a listing changes

Track any extension on Radar: users, rating, permissions and store text, with one email when something moves.

No credit card neededFree planAsk Claude on Pro