DNey Guard is now public in the Chrome Web Store. I've dog-fooded it for months myself, with my fam and a few friends.
DNey Guard is a free Chrome extension that checks what you send to ChatGPT and Claude for personal data, API keys, card numbers and prompt injection. It needs a free Dney account.
When you send a message on chatgpt.com or claude.ai, it checks the text you typed or pasted. If one of your protections fires, it blocks the message or masks the matching part, for example a Social Security number. Every new account starts with three protections switched on: prompt injection, personal data (masked on ChatGPT; on Claude, messages it would mask are blocked instead for now; card numbers are blocked on both), and data exfiltration (links or images that would send your conversation to another site, and API keys and tokens). You can change these and add others in your dashboard at dney.dev.
What it doesn't do: it checks text only, not the AI's replies, images, files or voice. ChatGPT's own tools (web search, code, connectors, deep research and agent mode) run on OpenAI's servers, so DNey Guard can't check them; it checks the messages you send. No filter catches everything. If Dney can't be reached, a personal install still sends your message and shows a warning banner so you know it wasn't checked.
Privacy: to check a message, DNey Guard sends its text to the Dney service, which uses OpenAI to run some of its checks. Dney doesn't store what you write. It keeps a record of each decision. Your API key is kept only in this browser on this device.
Free, no card.
Install: https://chromewebstore.google.com/detail/dney-guard-ai-guardrails/pelcglbblplfjhadghbclobecnljjebl
