# AI Red Teaming

Open-source diagnostic for AI operational misalignment

iFixAi is an Apache-2.0 diagnostic tool for scoring AI agents and models against operational-misalignment risks such as hallucination, manipulation, sabotage, sandbagging, and oversight evasion.

UK AI Security Institute framework for LLM safety evaluations

Inspect AI is an MIT-licensed framework from the UK AI Security Institute for running large language model evaluations, including tool use, multi-turn dialogue, model-graded scoring, and reusable evaluation tasks.

AI red teaming and infrastructure security scanner by Tencent

AI-Infra-Guard is Tencent's open-source AI security platform providing one-click evaluation of AI infrastructure risks across five modules. It covers insecure config detection, multi-agent workflow evaluation, MCP server scanning across 14 risk categories, vulnerability scanning for 55+ AI frameworks with 1,000+ CVE mappings, and jailbreak evaluation for prompt robustness. Deployable via Docker with academic backing from Peking and Fudan Universities.

Automated AI security testing and red teaming platform

Mindgard is an automated AI security testing platform that provides continuous red teaming for machine learning models and LLM applications. It detects vulnerabilities including adversarial attacks, prompt injection, data poisoning, and model extraction through systematic probing. Offers end-to-end testing across the AI lifecycle with enterprise compliance reporting and integration into CI/CD pipelines.