Tool
Horizon-Labs/prompt-injection-guard-base
Publication date unknown · Discovered huggingface.co
Page published
Publication date unknown · First observed: 19 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Prompt Injection Guard gives defenders a runnable screening layer for identifying suspicious instructions in user inputs and untrusted content before AI agents consume them.
Horizon-Labs’ Prompt Injection Guard base is an openly available, Apache-2.0-licensed 308M-parameter classifier for detecting direct prompt injections and jailbreaks, plus indirect injections in documents, RAG chunks, and tool outputs. The model card provides runnable integration examples, overlapping-window scanning for long documents, PyTorch and ONNX support, and reported benign-text evaluation results.