Learn the basic prompt-injection data leak pattern
Google Bard: prompt injection to data exfiltration · Security incident · Hacker News · wunderwuzzi23 · Nov 2023
A researcher showed a shared Google Doc could inject instructions into Bard and leak chat history through an image URL. Google fixed it.
Lesson
Don't let model output load external images or links that can carry data.
Fix prompt
Copy this into your own AI tool (Cursor, Lovable, Claude Code, Bolt…). It's general guidance written by us. Review what the AI suggests before applying it.
I use Google Bard, which can read web pages, files, emails or tool output. Help me reduce the risk of prompt injection (hidden instructions in content the AI reads). 1) List what my setup can access (files, terminal, browser, MCP servers, email, databases) and what it can do without asking me. 2) Point out the riskiest combinations, e.g. reading untrusted content while also having access to secrets or the ability to send data out. 3) Suggest concrete settings: require approval for commands and network calls, remove MCP servers I don't need, use read-only tokens, and keep the tool updated. 4) Give me a short checklist to follow before opening untrusted repos or documents. Don't change anything until I've approved your plan. Never ask me to paste API keys, passwords or .env contents; tell me where to check them myself.
Source: Hacker News ↗