Semantic-layer prompt injection defence that separates untrusted instructions from authority while preserving the legitimate task.
-
Updated
Jul 29, 2026 - Python
Semantic-layer prompt injection defence that separates untrusted instructions from authority while preserving the legitimate task.
Security-focused JSON UI DSL, validator, schemas, and React renderer for untrusted user- and LLM-generated content.
Add a description, image, and links to the untrusted-content topic page so that developers can more easily learn about it.
To associate your repository with the untrusted-content topic, visit your repo's landing page and select "manage topics."