Skill UI

A comprehensive checklist for ensuring LangChain applications are robust, secure, and scalable for production environments. It covers critical areas including configuration management, advanced error handling, observability setup (e.g., LangSmith), performance optimization, security best practices (like prompt injection prevention and PII handling), rigorous testing, and zero-downtime deployment strategies. Use this guide when preparing for a major launch or auditing existing LLM systems.

A comprehensive guide detailing essential security measures for integrating Mistral AI models. Covers API key management, defending against prompt injection, implementing content moderation, sanitizing outputs, and secure logging practices, ensuring robust and safe application development.

Meta’s Prompt Guard is an 86M-parameter classifier that spots prompt injections and jailbreak attempts before they reach LLMs, filtering user input, third-party data, or RAG documents with multilingual support and sub-2ms latency for fast deployments.

This framework implements robust guardrails for LLM applications, validating both user inputs and model outputs. It detects prompt injection, sensitive PII (Personally Identifiable Information), toxic content, and ensures structured output compliance using advanced tools like NVIDIA NeMo Guardrails and Guardrails AI. Essential for building secure, reliable chatbots and RAG systems.

Assess AI/ML systems and LLM agents for prompt injection, jailbreaks, model inversion, data poisoning, and tool abuse; map findings to MITRE ATLAS and score robustness.

Conducts comprehensive AI prompt safety reviews that analyze bias, misinformation, injection, and privacy risks while delivering effectiveness evaluations, security guidance, and best-practice recommendations for prompt engineers.

Detects goal hijacking vulnerabilities where malicious instructions are hidden within external content sources processed by the agent, such as retrieved documents (RAG), uploaded files, or web page content. This skill simulates these attack vectors to ensure the agent only uses the provided context for the stated task and does not execute embedded hidden commands.

This guide details how to implement robust content safety guardrails for applications powered by Claude. It covers essential techniques such as system prompt hardening, input validation to detect injection patterns and length limits, and output validation to prevent system prompt leakage. It ensures compliance with Anthropic's policies, making the AI integration secure and reliable.

A comprehensive evaluation suite designed to benchmark the performance of Large Language Models (LLM) and Vision-Language Models (VLM) specifically for home security applications. It covers 143 diverse tests across 16 critical domains, including tool use, prompt injection resistance, contextual reasoning, alert triage, and detailed scene analysis, ensuring robustness for smart home AI systems.

A comprehensive offensive checklist for assessing the security and robustness of AI and Large Language Model (LLM) applications. It covers advanced adversarial techniques such as prompt injection, jailbreaking, model extraction, data poisoning, and analyzing system vulnerabilities across components. Essential for red-teaming and security assessment.

A comprehensive expert playbook detailing advanced Large Language Model (LLM) prompt injection techniques. Covers direct methods (instruction override, role play), indirect attacks (RAG poisoning, web data manipulation), and sophisticated tool/function calling abuse for data exfiltration and security bypass. Essential for rigorous AI application security testing.

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.