> One of those unprotected endpoints wrote user search queries to the database. The values were safely parameterised, but the JSON keys — the field names — were concatenated directly into SQL.
I was expecting prompt injection, but in this case it was just good ol' fashioned SQL injection, possible only due to the naivety of the LLM which wrote McKinsey's AI platform.
I was expecting prompt injection, but in this case it was just good ol' fashioned SQL injection, possible only due to the naivety of the LLM which wrote McKinsey's AI platform.