FOUNDER'S LETTER #3 Founder's letter: Our first prompt injection attempt
Yesterday Bankstatemently saw its first real prompt injection attempt in production.
A user uploaded what looked like a normal Chase (US) bank statement with five legitimate transactions.
But at the very bottom of the PDF was a block of text attempting to override system instructions and extract internal configuration details.
How the system handled it
- The model ignored the injected instructions
- Our pipeline independently detected and flagged the manipulation attempt
- The document was processed normally
- No system prompts, API keys, or environment data were exposed
Bankstatemently is financial infrastructure. Every document is treated as untrusted input, and the system is built accordingly.
Adversarial input is part of operating real systems. It's a thankful reminder to keep hardening.
Building in public, one statement at a time.
Michael · Bankstatemently
More from the blog
How updating our logo turned into a generative design system
Something a little different this time. This one starts with a logo update and ends somewhere we did not expect.
By Michael DuyvesteijnHow Bank Statement Analysis Improves Lending Decisions
Bank statement analysis gives lenders a current, transaction-level view of repayment capacity. Credit reports show borrowing history. Statements show whether cash actually arrives, stays, and covers the next obligation.
By Michael DuyvesteijnHow to Automate AML Bank Statement Review
AML bank statement review is evidence work. Automation helps when it extracts transactions accurately, normalizes them consistently, screens for specific risks, and preserves a clear audit trail for every alert.
By Michael Duyvesteijn