{"name":"s3cr1z-ai-red-teaming-capabilities-ai-red-teaming","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"s3cr1z-ai-red-teaming-capabilities-ai-red-teaming","source":{"source":"github","repo":"s3cr1z/capabilities"},"description":"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.","version":"1.2.0","strict":true,"keywords":["ai-red-teaming","airt","llm-security","adversarial","safety","owasp","owasp-asi","mitre-atlas","compliance","jailbreak","prompt-injection","mcp-security","multi-agent","agentic"],"category":"productivity"}]}