Toolverse
All skills

prompt-guard

by Orchestra-Research

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, u003c1% FPR. Fast (u003c2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Installation

Pick a client and clone the repository into its skills directory.

Installation

Quick info

Category
Security
Views
3

About this skill

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, u003c1% FPR. Fast (u003c2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

How to use

  1. Zainstaluj wymagane biblioteki, uruchamiając w terminalu polecenie pip install transformers torch. 2. Załaduj model i tokenizer z HuggingFace, korzystając z identyfikatora meta-llama/Prompt-Guard-86M. Zainicjuj model w trybie ewaluacji, aby wyłączyć uczenie. 3. Przygotuj funkcję, która przyjmuje tekst wejściowy, tokenizuje go z maksymalną długością 512 znaków i przekazuje do modelu. 4. Oblicz prawdopodobieństwo jailbreak z trzeciego wyjścia modelu (indeks 2) za pomocą softmax. 5. Ustaw próg decyzji (zazwyczaj 0,5) i porównaj wynik: jeśli prawdopodobieństwo przekracza próg, oznacza to wykrycie próby jailbreak. 6. Zintegruj filtrowanie z potokiem aplikacji, aby blokować niebezpieczne dane wejściowe przed przekazaniem ich do modelu językowego.

Related skills

youtube-watcher

by openclaw

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

Security
2231

openapi-spec-generation

by wshobson

Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.

Security
18109

senior-security

by davila7

Comprehensive security engineering skill for application security, penetration testing, security architecture, and compliance auditing. Includes security assessment tools, threat modeling, crypto implementation, and security automation. Use when designing security architecture,

Security
2482

academic-researcher

by Shubhamsaboo

Academic research assistant for literature reviews, paper analysis, and scholarly writing.\nUse when: reviewing academic papers, conducting literature reviews, writing research summaries,\nanalyzing methodologies, formatting citations, or when user mentions academic research,

Security
1260

content-creator

by alirezarezvani

Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content

Security
25124

feishu-docs

by openclaw

飞书文档(Docx)API技能。用于创建、读取、更新和删除飞书文档。支持Markdown/HTML内容转换、文档权限管理。

Security
1574