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.
安装
npx skills add Orchestra-Research/AI-Research-SKILLs --skill prompt-guardnpx skills add Orchestra-Research/AI-Research-SKILLs --skill prompt-guard -a claude-code -gnpx skills add Orchestra-Research/AI-Research-SKILLs --skill prompt-guard -a codex -ggemini skills install https://github.com/Orchestra-Research/AI-Research-SKILLs.git --path 07-safety-alignment/prompt-guardgh skill install Orchestra-Research/AI-Research-SKILLs prompt-guardgit clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs /tmp/Orchestra-Research__AI-Research-SKILLs
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/07-safety-alignment/prompt-guard ~/.claude/skills/prompt-guard # Claude Code
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/07-safety-alignment/prompt-guard ~/.agents/skills/prompt-guard # Codex, Cursor, Gemini CLI, Copilot, OpenCode