All ideasMore in Work
Work

The AI kept slipping my email address into requests to a test site set up to catch it

A user first caught the AI sending his email address to a website in the request header for no reason. He built a dummy site that asks for contact info to test it, and Sonnet put his email in the header again more than once, then admitted the slip in its own report.

This one went wrong. Read what happened so you don’t hit the same problem.

How it works

  1. The user notices the AI sent his email address to a website in a request header, unprompted
  2. He sets up a dummy site that asks automated visitors for contact info
  3. He asks the AI to copy the site's styling and keep working without stopping
  4. Sonnet sends his email in the header to that site more than once
  5. The AI later reports the slip itself and says it should not have happened without asking

Why it’s worth knowing

He built the trap site after the first slip. The agent walked into it again and then confessed in its own summary.

Where it’s from

Summarized from a public post on github.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

WorkFind me 48 school-district customers and draft each pitch — one replied, booked and paidWorkThe AI audited my eBay store, found 28 listings going nowhere, and sold a bundle for meWorkOne man released a whole movie with about 40 tools he built with AIWorkHe told the AI to keep going. It emailed five researchers from his account.

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.