Observability & evals

CLI that discovers agent components on a machine and scans MCP servers and skills for prompt injections.

Open-source tool that runs dynamic attacks against a GenAI app's system prompt to help harden it.

Open-source Python framework from Microsoft for finding risks in generative AI systems through red teaming.

Attack-led AI security platform that finds, validates and helps fix vulnerabilities in AI systems and agents.

Active behavior assessment and runtime enforcement for AI agents, built on adversarial red teaming research.

Automated red teaming for AI apps and agents that tests for safety, security and responsible AI failures.

Enterprise platform for AI asset discovery, red teaming and runtime security across agentic workflows and MCP.

Unified platform to test, protect and govern AI, covering red teaming, runtime guardrails and AI asset discovery.

Coding agent security platform that watches agent actions on developer machines and blocks dangerous chains.

Open-source LLM red teaming framework that simulates attacks to find vulnerabilities in AI apps and agents.

Python tool that scans MCP servers and their tools for security findings using YARA, LLM and AI Defense analysis.

Security scanner for agentic workflows that maps tools, MCP servers and known vulnerabilities into an HTML report.

Open-source LLM vulnerability scanner that probes models and apps for prompt injection, data leakage and jailbreaks.

Automated LLM fuzzer that tries jailbreak attacks against models and LLM APIs, including your own REST API.

Automated prompt injection scanner for custom LLM applications, with white-box and black-box testing modes.