Blog

#3 Founder's letter: Our first prompt injection attempt

Published: February 27, 2026

·1 min read

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

Terminal output showing Bankstatemently VLM pipeline detecting and rejecting an embedded prompt injection attempt in a fake Chase bank statement
  • 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