What's safe to paste into an AI tool
Most of what you’d share in a screen-share is safe to paste into a hosted AI tool. This page names the exceptions — the categories that need to stay out of the prompt, and what to do the day something slips.
Recommended default
Section titled “Recommended default”Assume anything you paste into a hosted AI tool leaves your control. Paste what you’d be comfortable seeing in a support-ticket export; keep the rest out. When the only useful prompt would need something in the “keep out” list, that’s a signal to close the tab, not to redact harder.
What to keep out
Section titled “What to keep out”- Secrets and credentials. API keys, tokens, private keys, connection strings. If one lands in a chat, rotate it — deleting the message isn’t enough.
- Customer data. Names, emails, PII, order IDs. Even one-line snippets from a production log usually carry more than the line suggests.
- Unreleased IP. Internal-only APIs, unshipped product code, roadmap detail. Treat the paste like a public blog post.
- Licence-restricted code. Copyleft snippets or third-party proprietary code. Both create obligations you don’t want the model quoting back into your own diff.
Common mistakes
Section titled “Common mistakes”- Redacting only the obvious.
[email protected]looks fine; the stack trace above it still names the customer. - Trusting “private” chats. Read the tool’s retention and training terms before you rely on the label.
- Assuming you’ll remember. Once a secret is in a chat, treat it as leaked and rotate — even if you deleted the message.
What to do after a slip
Section titled “What to do after a slip”- Rotate the secret or revoke the token.
- Delete the message where you can; assume the model still saw it.
- Note the workflow that let it in. The second incident is the one that matters.