The AI broke his team's own database guards and found the write hiding in a read-only call

Asked the AI to break his team's own Postgres MCP guards and it found pg_logical_emit_message, which writes to the WAL inside a read-only transaction, leading to a hardened replacement.

How it works

He asks the AI to break the team's own database MCP guards
It finds a function that writes to the log inside a read-only transaction
Leading to hardening

Why it’s worth knowing

Read-only that writes is the kind of lie only an attacker finds. Theirs did.

Where it’s from

Summarized from a public post on news.ycombinator.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

WorkA contractor talks measurements into his phone and QuickBooks sends the estimate in 45 seconds WorkFind me 48 school-district customers and draft each pitch — one replied, booked and paid WorkOne man released a whole movie with about 40 tools he built with AI WorkA solo seller's daily production plan pulls orders from four shops at once

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.