Prompt Injection, Hands-On: Attacking My Own Model With Bedrock Guardrails
I had read enough prompt-injection. I still wanted to poke at a real filter and keep the bill and the teardown small.
I stood up a Bedrock Guardrail on the Standard tier, pointed Claude Haiku 4.5 at it through Converse, and ran a JSON matrix of 34 prompts. Create the guardrail, fire the matrix, score the CSV, delete everything. The repo is github.com/sprider/bedrock-prompt-injection-lab .
- Guardrail with
PROMPT_ATTACKat HIGH, plus content and PII filters - Converse with a plain customer-support system prompt
- User text wrapped in
guardContentso prompt-attack filtering applies to user input, not the system text - One command up, one command down. Agents Classic is in maintenance mode and closed for new agents on many accounts, so this lab stays on Converse.
Enjoyed reading this content? Let the author know!
Your likes, comments, shares, and saves help creators reach more builders.
Loading recommendations
Loading article