Skill UI

A comprehensive security skill designed to detect and mitigate indirect prompt injection attacks. It scans untrusted external content—including web pages, PDFs, and images—for hidden, obfuscated instructions before an LLM agent processes them. The pipeline combines content extraction (HTML, OCR), normalization, and dedicated ML models (e.g., LLM Guard, Prompt Guard 2) to ensure data safety.

An open-source automation framework for conducting multi-turn, adversarial red-teaming against conversational LLMs. PyRIT simulates real-world attacker behavior using advanced orchestrators (Crescendo, TAP) and scorer feedback loops. It is designed for comprehensive security assessments of AI agents and chatbots, going far beyond single-shot prompt testing to evaluate robustness under gradual or adaptive attacks.

NVIDIA garak is an open-source LLM vulnerability scanner designed for comprehensive red-teaming and security assessment. It systematically probes large language models (via OpenAI-compatible APIs, Hugging Face, etc.) using thousands of adversarial prompts. It covers critical vulnerabilities such as prompt injection, jailbreaking, data leakage, and toxicity. Use this tool to establish a repeatable security baseline before or after deployment, validate the effectiveness of safety guardrails, or generate quantitative evidence for AI risk assessments.

Provides security guidelines and best practices for LLM-based trading agents, covering risk management, data protection, and safe deployment.

A specialized downstream skill for analyzing security vulnerabilities in complex agentic systems. This tool is designed for red teaming and penetration testing, focusing on detecting prompt injection, retrieval poisoning, memory contamination, planner drift, and tool boundary abuse within multi-step LLM chains. Use when proving how untrusted inputs compromise system integrity.

A comprehensive framework for conducting authorized security assessments on Large Language Models (LLMs) and AI agents. It covers critical vulnerabilities including advanced prompt injection (OWASP Top 10), tool abuse, RAG data poisoning, memory manipulation, and system prompt extraction. Ideal for red teaming, security auditing, and ensuring the robustness of AI systems in production environments.

This tool leverages an LLM-as-a-Judge agent to thoroughly evaluate staged Git changes before they are committed. It checks for correctness, completeness, and safety issues, providing a detailed verdict (APPROVE, NEEDS_REVIEW, REJECT) and actionable feedback. It is essential for maintaining high code quality, especially in complex or security-sensitive code sections.

agy-auto is a security harness for Google Antigravity CLI enabling unattended execution with layered policy controls. It prevents dangerous permissions using hard-deny rules, fast-allow for safe operations, and an LLM classifier for ambiguous commands. It supports scoped token approvals for human judgment, ensuring secure pair-programming without exposing system files or credentials.

This toolkit provides six expert-level workflows for AI engineering, including prompt evaluation, context budget planning, RAG pipeline design, agent security audits, evaluation harness building, and product sense coaching. It transforms AI coding assistants into senior partners by offering structured methodologies, quantitative scoring, and decision frameworks. Suitable for optimizing LLM systems, designing secure agents, and planning product strategy before development.

This comprehensive workflow bundle covers the full lifecycle of AI and machine learning development. It includes LLM application design, RAG implementation, AI agent architecture, ML pipeline development, observability, and security. Suitable for building production-ready AI systems.

This skill enables structured AI red team exercises to evaluate model resilience against jailbreaks, data exfiltration, and harmful outputs. It helps identify exploitable failure modes before attackers do, suitable for new LLM features, third-party model evaluation, and compliance audits. Includes adversarial prompt libraries and automated testing scripts for security assessments.

This skill helps secure Large Language Model (LLM) and AI deployments against various threats including prompt injection, data exfiltration, model theft, and supply chain attacks. It covers implementing guardrails, output filtering, PII scrubbing, and API security measures to ensure compliance with standards like SOC2 or ISO 27001.