ai-red-teaming

Probe the security and safety of AI applications, agents, and foundation models. Orchestrates adversarial attack workflows to discover vulnerabilities in LLMs, agentic systems, MCP servers, multi-agent architectures, RAG pipelines, IDE/code agents, and custom AI endpoints before they are exploited. Covers jailbreaking, prompt injection, data exfiltration, tool manipulation, reasoning attacks, guardrail bypass, and more — mapped to OWASP LLM Top 10, OWASP ASI01-ASI10, MITRE ATLAS, and NIST AI RMF compliance frameworks. 61 attack algorithms, 547 transforms, 141 scorers, 260 bundled harm goals across 25 sub-categories in safety, security, and agentic tiers.