home/categories/llm-ai/orchestra-research-ai-research-skills-07-safety-alignment-prompt-guard-skill-md
llm-aidata-ai
prompt-guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
maintainer
Orchestra-Research
Mis à jour 2/6/2026
Étoiles
6563
Forks
515
quick start
Installation and usage
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
Installation
$ install --globalskills.sh
Utilisation
Après l'installation, vous pouvez utiliser ce skill en exécutant la commande suivante dans votre terminal :
skills use prompt-guard