Verified record · from the answer index

prompt-guard

skilltested · static-verifiedscore 49/100signed passport ✓931 uses

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.

Declared tools (1)

prompt-guard

skill:orchestra-research/ai-research-skills/prompt-guard · published by orchestra-research · source repository