🛡️Vigil
⚡ Security scanner for Large Language Model (LLM) prompts ⚡
Last updated
⚡ Security scanner for Large Language Model (LLM) prompts ⚡
Last updated
Vigil
is a Python library and REST API for assessing Large Language Model prompts and responses against a set of scanners to detect prompt injections, jailbreaks, and other potential risks. This repository also provides the detection signatures and datasets needed to get started with self-hosting.
This application is currently in an alpha state and should be considered experimental.
Work is ongoing to expand detection mechanisms and features.
Analyze LLM prompts for common injections and risky inputs
Use Vigil as a Python library or REST API
Evaluate detections and pipelines with Vigil-Eval (coming soon)
Scanners are modular and easily extensible
Available scan modules
Supports local embeddings and/or OpenAI
Signatures and embeddings for common attacks
Custom detections via YARA signatures