Vigil
StaleDescription
Vigil is an LLM security detection tool that identifies prompt injections, jailbreaks, and other potentially risky LLM inputs through multi-dimensional analysis for real-time safety protection.
Related Projects
Prompt Guard
152 · Python
Advanced prompt injection defense system for AI agents with multi-language detection, severity scoring, and security auditing.
prompt-injectionsecurityguardrails +2
Open-Prompt-Injection
439 · Python
An open-source benchmark for prompt injection attacks and defenses in LLMs, systematically evaluating the effectiveness of different attack strategies and defense mechanisms.
prompt-injectionbenchmarkllm-safety +2
Pytector
40 · Python
Easy to use LLM prompt injection detection and prompt input sanitization Python package with multiple detection methods and custom rules.
prompt-injectiondetectionsanitization +2
NeMo Guardrails
6.1k · Python
NVIDIA NeMo Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational systems, supporting topic control, safety enforcement, and dialog guidance.
guardrailsllm-safetynvidia +2