Skill UI

This tool facilitates comprehensive purple team exercises by executing Atomic Red Team tests mapped to MITRE ATT&CK techniques. It is primarily used for gap analysis, validating detection coverage (blue team visibility) against specific threat vectors, and building continuous, automated adversarial emulation pipelines in CI/CD environments.

This skill transforms AI from a validating assistant into a relentless adversary. Ideal for stress-testing high-stakes decisions, business plans, or core assumptions. It forces the model to produce the strongest case against your position, identifying potential failure points and required proofs, ensuring you confront the risks you might otherwise ignore.

This skill utilizes NVIDIA's open-source garak framework to conduct comprehensive red-teaming assessments on Large Language Models (LLMs). It tests for critical vulnerabilities such as prompt injection, jailbreaks, data leakage, and toxic content generation by sending thousands of adversarial probes. Ideal for pre-deployment security validation, API guardrail testing, and generating defensible evidence for AI risk assessments.

This skill performs an adversarial audit of web application authentication flows. It systematically probes for critical security vulnerabilities such as missing CSRF protection, insecure session cookies (lacking Secure/HttpOnly flags), risky cross-origin redirects, and OAuth misconfigurations. It generates a structured report detailing findings and severity levels, making it ideal for pre-deployment security audits and regression testing.