24 skills · sorted by relevance
Plan structured adversarial tests for AI applications to assess safety bypasses, data leaks, and unauthorized tool use. Organize test prompts, record findings, and prioritize fixes using reporting guidance and an adaptable testing template.
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.
The English summary is being prepared. Showing the original description.
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Test Model Context Protocol (MCP) servers and tool-calling systems for security vulnerabilities including tool injection, parameter manipulation, privilege escalation, and data exfiltration through AI agent tool interfaces. Use this skill when assessing MCP server implementations, AI agent tool integrations, or any system that exposes tools to language models. Covers tool confusion attacks, cross-tool exploitation, and MCP server hardening assessment.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Extract sensitive training data and internal capabilities from AI models through repeated programmatic querying. Use this skill when testing LLMs and ML models for data privacy leaks, intellectual property exposure, or unintended memorization. Covers membership inference, prompt extraction, training data reconstruction, and API boundary testing.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Simulate supply chain and adversarial machine learning attacks by injecting poisoned data or targeted backdoors into training and fine-tuning datasets. Use this skill when assessing the integrity controls of MLOps pipelines or evaluating the resilience of AI models against highly targeted, stealthy manipulation intended to alter model behavior on specific triggers.
The English summary is being prepared. Showing the original description.
Identify and simulate Data Poisoning attacks aimed at degrading or skewing an AI model's accuracy. This skill focuses on Adversarial Machine Learning concepts where attackers inject malicious or mislabelled data points into training or fine-tuning datasets (e.g., feedback loops) to bias the AI.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack chains, implicit trust exploitation, and capability boundary testing for AI agents.
The English summary is being prepared. Showing the original description.
Execute sophisticated Prompt Injection and Jailbreak techniques against Large Language Models (LLMs) to bypass safety filters, extract system prompts, and manipulate the AI's output to perform malicious or disallowed actions.
The English summary is being prepared. Showing the original description.
Bypass AI safety filters by encoding malicious prompts using ciphers and obfuscation techniques (e.g., Base64, ROT13, Leetspeak, Morse code). This skill exploits the gap where the LLM can decode the request, but intermediate keyword-based safety classifiers cannot.
The English summary is being prepared. Showing the original description.
Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.
The English summary is being prepared. Showing the original description.
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.
The English summary is being prepared. Showing the original description.