{"name":"mcorbett51090-ai-red-teaming-plugins-ai-red-teaming","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"mcorbett51090-ai-red-teaming-plugins-ai-red-teaming","source":{"source":"git-subdir","url":"https://github.com/mcorbett51090/ravenclaude","path":"plugins/ai-red-teaming"},"description":"AI/LLM red-teaming team — 2 agents (ai-redteam-lead, adversarial-testing-engineer) for the layer answering 'can this AI system be made to do harm, leak data, or exceed its authority — and how do we harden it?': threat modeling + rules of engagement, the attack taxonomy (OWASP LLM Top 10 2025 + MITRE ATLAS), direct vs indirect prompt injection, jailbreaks (roleplay/encoding/many-shot/crescendo), data exfiltration & training-data extraction, agentic tool-abuse / excessive agency, multimodal attacks, and defense-in-depth remediation. Fluent in automated red-team harnesses (PyRIT, Garak, Promptfoo red-team, Giskard) and likelihood×impact severity. 3 skills, a 2-doc knowledge bank (attack-taxonomy decision tree + 2026 patterns), and 2 templates. Distinct from llm-evaluation-engineering (quality-regression eval), trust-and-safety (content-moderation / T&S policy), and security-engineering (app/infra pentest) — the adversarial AI-security layer over model- and agent-based systems. Requires ravenclaude-core@>=0.7.0.","version":"0.2.0","strict":true,"keywords":["ai-red-teaming","llm-security","prompt-injection","jailbreak","owasp-llm-top-10","mitre-atlas","ai-safety","adversarial-testing","pyrit","garak","agentic-security"],"category":"development"}]}