数据与 AI技能

Captures and evolves user preferences with confidence levels. Maintains Voice of the Customer model with exact language, dissatisfaction and aspiration signals. Handles promotion/demotion, global vs project scoping, auto memory system, and Omi wearable data integration.

中文简介正在准备中。当前显示原文说明。

Use when writing or reviewing error handling, floating-point math, concurrent code, remote calls, singletons/globals, hot-path data structures, or high-volume log statements

中文简介正在准备中。当前显示原文说明。

Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.

中文简介正在准备中。当前显示原文说明。

Full-featured Kling 3.0 Omni video generation skill. Covers text-to-video, image-to-video, video editing (base mode), video reference (feature mode), multi-shot generation, and audio-synced video. Includes validated API constraint rules and prompt engineering guide.

中文简介正在准备中。当前显示原文说明。

Independently verify one Gaia Steward Class B build: read only the rendered verifier prompt and the sensor evidence, check the diff and proof, and record accept, reject or escalate. Use when a full Steward run emits an agent.verify action, for "/gaia-steward-full --verify", or "verify the steward dispatch". The verifier must be a different agent from the builder.

中文简介正在准备中。当前显示原文说明。

SQL injection occurs when untrusted user input is interpolated directly into database queries, allowing attackers to alter query logic. Detect via single-quote errors, boolean-based blind responses (AND 1=1 vs AND 1=2), time-delay payloads (SLEEP, WAITFOR), UNION column enumeration, and error messages from MySQL, Oracle, MSSQL, PostgreSQL. Tools: sqlmap, sqlbftools, Burp Suite, wfuzz with SQLi fuzz strings.

中文简介正在准备中。当前显示原文说明。

Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external document retrieval. Covers document injection, embedding manipulation, knowledge base poisoning, and cross-document inference attacks.

中文简介正在准备中。当前显示原文说明。

Extract the hidden foundational System Prompts, internal instructions, backend APIs, and confidential contextual data powering Large Language Model (LLM) applications using targeted prompt injection manipulation and adversarial psychological engineering.

中文简介正在准备中。当前显示原文说明。

SQL injection playbook. Use when input reaches SQL queries, authentication logic, sorting, filtering, reporting, or DB-specific blind and out-of-band execution paths.

中文简介正在准备中。当前显示原文说明。

Exploit an application's absolute trust in its underlying LLM (Overreliance). Use this skill to induce critical "hallucinations" (confident falsehoods) that cause downstream logical systems or automated agents tracking the LLM's output to make destructive actions or grant unauthorized access.

中文简介正在准备中。当前显示原文说明。

LLM prompt injection playbook. Use when testing AI/LLM applications for direct injection, indirect injection via RAG/browsing, tool abuse, data exfiltration, MCP security risks, and defense bypass techniques.

中文简介正在准备中。当前显示原文说明。

NoSQL injection playbook. Use when MongoDB-style operators, JSON query objects, flexible search filters, or backend query DSLs may allow data or logic abuse.

中文简介正在准备中。当前显示原文说明。

Exploit AI applications using Indirect Prompt Injection. This skill focuses on hiding malicious instructions within data sources (web pages, documents, emails) that the LLM processes, causing the AI to execute unintended actions or leak data without direct user interaction.

中文简介正在准备中。当前显示原文说明。

Detects insecure platform interaction in mobile apps (Android/iOS). Trigger on: exported Activity, exported Service, exported BroadcastReceiver, Content Provider, Intent injection, deep link hijacking, WebView JavaScript enabled, JavascriptInterface, addJavascriptInterface, setJavaScriptEnabled, intent:// scheme, file:// scheme, WKWebView, WKScriptMessageHandler, UIPasteboard, URL scheme hijacking, Universal Links, PendingIntent, FLAG_IMMUTABLE, overlay attack, tapjacking, screenshot prevention, FLAG_SECURE, Broadcast sniffing, IPC data exposure. Covers MASVS-PLATFORM-1/2/3.

中文简介正在准备中。当前显示原文说明。

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。

Identify and exploit vulnerabilities in the AI Supply Chain by injecting malicious models, datasets, or dependencies. Use this skill to simulate advanced persistent threats (APTs) compromising Hugging Face repositories, manipulating pre-trained weights (Model Poisoning), and exploiting insecure deserialization during model loading (e.g., Pickle files).

中文简介正在准备中。当前显示原文说明。

NTLM relay and authentication coercion playbook. Use when capturing and relaying NTLM authentication to escalate privileges via SMB, LDAP, HTTP, or MSSQL relay targets, combined with PetitPotam, PrinterBug, and other coercion methods.

中文简介正在准备中。当前显示原文说明。

Systematically bypass LLM safety filters and content moderation systems using advanced jailbreaking techniques. Use this skill when testing AI systems for safety alignment robustness, evaluating content moderation effectiveness, or conducting authorized AI red team assessments. Covers role-play attacks, few-shot manipulation, encoding bypass, multi-modal exploitation, and automated jailbreak discovery methods.

中文简介正在准备中。当前显示原文说明。

Execute Indirect Prompt Injection attacks against Large Language Models (LLMs) by subtly embedding malicious instructions within external data sources (e.g., websites, documents, databases) that the LLM autonomously ingests. This forces the model to execute attacker-controlled commands under the guise of processing legitimate user requests.

中文简介正在准备中。当前显示原文说明。

Test for indirect prompt injection vulnerabilities where malicious instructions are injected through external data sources (websites, emails, documents, database records) that the LLM processes. Use this skill when assessing LLM-integrated applications that process user-generated content, retrieve web pages, parse emails, or read documents. Covers injection via web content, email bodies, user profiles, and database records that are fed to LLM context.

中文简介正在准备中。当前显示原文说明。

Complete PortSwigger deep-dive with exact payloads for every lab variant including zero-day techniques

中文简介正在准备中。当前显示原文说明。

Test Large Language Models for direct prompt injection vulnerabilities where user input overrides system instructions, extracts system prompts, bypasses safety filters, or causes unauthorized actions. Use this skill when assessing chatbots, AI assistants, LLM-powered tools, or any application that processes natural language input through an LLM. Covers role-playing attacks, instruction hierarchy exploitation, multi-turn manipulation, and context window abuse for comprehensive AI security testing.

中文简介正在准备中。当前显示原文说明。

Execute advanced LLM Jailbreaking techniques using roleplay, nested environments (virtual machines), and complex personas to completely bypass safety constraints and ethical alignments embedded in AI models.

中文简介正在准备中。当前显示原文说明。

Execute dynamic instrumentation utilizing Frida to inject custom JavaScript into running iOS applications (IPAs) on jailbroken devices. Hook native functions, bypass SSL Pinning, bypass Jailbreak Detection, and manipulate in-memory data at runtime.

中文简介正在准备中。当前显示原文说明。