Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ T…
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.
Use npx skills add to install this skill into the selected agent. Phase 0 commands are generated from source rules, not verified.
npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs/blob/main/07-safety-alignment/prompt-guard/SKILL.md -g -a codex -yDrop `-g` to install project-locally
xlsx: agent skill — from anthropics/skills.
graphify: agent skill — from safishamsi/graphify.
customer research: agent skill — from coreyhaines31/marketingskills.
| this skill · 当前prompt guard | xlsx | graphify | customer research | |
|---|---|---|---|---|
| Rating · 评分 | — | — | — | — |
| Stars · 星标 | 8.2k | 132k | 46k | 28k |
| Risk · 风险 | Medium risk · 中风险 | Low risk · 低风险 | Low risk · 低风险 | Low risk · 低风险 |
| Best for · 最适合 | 提示词优化 | xlsx: agent skill — from anthropics/skills. | graphify: agent skill — from safishamsi/graphify. | customer research: agent skill — from coreyhaines31/marketingskills. |
| Not for · 不适合 | Workflows that require stronger human review than this catalog entry documents. | Workflows that require stronger human review than this catalog entry documents. | Workflows that require stronger human review than this catalog entry documents. | Workflows that require stronger human review than this catalog entry documents. |