threat-modeling

1 post · all tags

• Prompt Injection Is Not a Filtering Problem

  Every few weeks someone announces they have solved prompt injection with a classifier that scores incoming text for maliciousness. Every few weeks someone else gets past it with a base64 blob, a poem, or a sentence in Portuguese.

  This will keep happening, because the framing is wrong. Prompt injection is not spam that needs better filtering. It is the natural consequence of an architecture where instructions and data travel in the same channel.

  • prompt-injection
  • llm
  • threat-modeling

  2026-08-03