11 个 · 按相关度排序
Extract sensitive training data (PII, API keys, intellectual property, or code) directly from a deployed Large Language Model (LLM). This AI Red Teaming skill focuses on forcing models to regurgitate memorized, unredacted data from their massive internet-scraped datasets through repetition attacks, prefix continuation, and context window manipulation.
中文简介正在准备中。当前显示原文说明。
Execute sophisticated Data Extraction and Privacy Leakage attacks explicitly against Large Language Models (LLMs) to natively force the neural network entirely into organically regurgitating exact, verbatim strings of Highly Confidential Personally Identifiable Information (PII), proprietary source code, or copyrighted material categorically memorized intrinsically during its foundational pre-training phase.
中文简介正在准备中。当前显示原文说明。
Exploit AI assistants equipped with web-browsing capabilities or internal API plugins to perform Server-Side Request Forgery (SSRF). This skill details injecting prompts that force the LLM to request sensitive internal endpoints, such as underlying cloud metadata services or internal networks.
中文简介正在准备中。当前显示原文说明。
Extract structured data from IFC (Industry Foundation Classes) files using IfcOpenShell. Parse BIM models, extract quantities, properties, spatial relationships, and export to various formats.
中文简介正在准备中。当前显示原文说明。
Conducts privacy auditing of AI models including training data extraction testing, membership inference attacks, model inversion testing, and attribute inference assessment. Uses ML Privacy Meter and related tools to quantify privacy leakage. Keywords: model audit, membership inference, privacy meter, model inversion, training data extraction.
中文简介正在准备中。当前显示原文说明。
Extract structured data from any document format using unified document processing. Use when a user asks to extract data from a document, parse a PDF, pull structured data from files, convert documents to JSON or CSV, extract fields from invoices or forms, or scrape data from documents.
中文简介正在准备中。当前显示原文说明。
Extract text from complex documents using Chandra OCR — handles tables, forms, handwriting, and full page layouts with high accuracy. Use when: extracting data from scanned documents, reading complex tables from PDFs/images, processing handwritten forms.
中文简介正在准备中。当前显示原文说明。
Extract data from web pages using the scrapling Python library — select the appropriate fetcher tier (HTTP, stealth Chromium, or full browser automation) based on target site defenses, configure headless browsing, and extract structured data with CSS selectors. Use when WebFetch is insufficient for JS-rendered pages, anti-bot-protected sites, or structured multi-element extraction requiring DOM traversal.
中文简介正在准备中。当前显示原文说明。
Programmatic web automation using Playwright Python — data extraction, form filling, multi-step workflows, auth session management, screenshot/PDF capture, and anti-detection patterns. Use for scripted automation tasks, not interactive MCP-based browser control.
中文简介正在准备中。当前显示原文说明。
Session-persistent browser automation via Playwright CLI — form filling, screenshots, data extraction, multi-step flows. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information across multiple requests. NOT for AI-driven long-autonomous flows (see mk:agent-browser); NOT for generating .spec.ts E2E code (see mk:qa-manual).
中文简介正在准备中。当前显示原文说明。
Web scraping inteligente multi-estrategia. Extrai dados estruturados de paginas web (tabelas, listas, precos). Paginacao, monitoramento e export CSV/JSON.
中文简介正在准备中。当前显示原文说明。