DocBot

Headlines · 1

1. 3d
   OpenRouter tests Armor against prompt-injection attacks

   OpenRouter evaluated 25 prompt-injection attacks against four models using a document-summarizing assistant, comparing configurations with defenses enabled and disabled. Its Armor tool-call filter reduced successful attack emails from 73 of 1,440 attempts to zero, while labeling documents as data alone left 13 of 720 attempts successful. Armor allowed nearly every explicitly requested email but blocked one legitimate request because the user had not named the recipient address.

   OpenRouter Blog · 🔥 0

Experience and discussion from the community

Share my DocBot experienceAsk about DocBot