Adversarial testing for LLM applications. Calibrated prompt-injection and jailbreak scans with reproducible reports. Pip install, async-first, framework-agnostic.
-
Updated
May 20, 2026 - Python
#
lm-security
Here are 2 public repositories matching this topic...
This repository documents AI Recommendation Poisoning — a real-world attack technique discovered by Microsoft's Defender Security Research Team (February 2026) where adversaries silently inject persistent instructions into AI assistant memory through carefully crafted URLs.
-
Updated
Mar 27, 2026 - HTML
Improve this page
Add a description, image, and links to the lm-security topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the lm-security topic, visit your repo's landing page and select "manage topics."