Understand zero-click leaks in AI assistants
EchoLeak: zero-click data leak from Microsoft 365 Copilot · Security incident · Hacker News · aimsecurity · Jun 2025
Aim Security found a crafted email could make M365 Copilot leak data from the user's context without any click (CVE-2025-32711). Microsoft fixed it server-side.
Lesson
Assume any email or document an assistant reads can carry instructions; limit what it can access.
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 Microsoft 365 Copilot, 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 ↗