Decepticon Autonomous Red Team Agent
Plans and executes complete red-team attack chains within an authorized engagement scope.
T3MP3ST Security Harness
Turn a connected coding agent into an orchestrated workflow for authorized security testing.
Anthropic Cybersecurity Skills
817 structured cybersecurity skills for AI agents, spanning 29 domains and 6 frameworks.
RAMPART
A pytest-native safety and security testing framework that brings adversarial and benign-failure coverage to agentic AI apps in your existing test workflow.
AI-Infra-Guard (A.I.G) – AI Red Teaming Platform by Tencent Zhuque Lab
Full-stack AI security self-inspection: OpenClaw security scan, agent/MCP/skill scan, AI infra vulnerability scan, and jailbreak evaluation.
Giskard
Evaluate, red-team, and generate tests for LLM-powered and multi-turn agent systems.
RagaAI Catalyst
A Python SDK for evaluating, tracing, debugging, and safety-testing LLM and multi-agent applications.
Agentic Security
Open-source vulnerability scanner for LLMs and agent workflows, detecting jailbreaks, fuzzing, and multimodal attacks.
Rogue — AI Agent Evaluator & Red Team Platform
Stress-test your AI agents before attackers do, with automated evaluation and red teaming.
Superagent SDK
Secure AI applications against prompt injection, sensitive-data exposure, and repository-borne threats.
Cairn — General State-Space Search Engine
A general-purpose problem-solving engine for well-defined origins and goals, proven on autonomous penetration testing.
Agent Learning Kit
Local-first simulation, evaluation, red teaming, and optimization for AI agents.
DeepTeam - LLM Red Teaming Framework
An open-source framework for pen-testing LLMs and AI agents with simulated attacks like jailbreaking and prompt injection, plus production guardrails.