ai-security Tools

AiSOC is an open-source AI Security Operations Center platform that makes AI-driven security investigations transparent and auditable. It solves the problem of 'black-box' AI security tools by recording every agent step—prompts, tool calls, and reasoning—in a replayable investigation ledger, enabling compliance with SOC 2, ISO 27001, and DORA. It's built for security teams in regulated environments who need the power of AI agents but require full auditability and the ability to self-host.

SkillSpector is a security scanner that detects vulnerabilities and malicious patterns in AI agent skills for platforms like Claude Code and MCP. It solves the problem of installing risky skills that may contain hidden instructions, data exfiltration, or supply-chain threats. It's for developers, security teams, and anyone deploying AI agents who needs to vet third-party skills for safety.

AI-Infra-Guard is a comprehensive red teaming platform designed to secure modern AI ecosystems. It identifies vulnerabilities across AI agents, skills, MCP servers, underlying infrastructure, and LLM jailbreak risks. This platform is essential for security teams, AI developers, and enterprises deploying AI to ensure their systems are robust and resilient against emerging threats.

Strix is an open-source AI penetration testing platform that continuously finds and fixes vulnerabilities across your code, APIs, web apps, and cloud infrastructure. It automates security testing on every deploy, providing proof-of-exploit for findings and even generating merge-ready fix suggestions. It's designed for security and development teams who need to secure their full application stack proactively and at scale.

ADR is a production-proven system for securing enterprise AI agents built on the Model Context Protocol (MCP). It solves the critical challenges of limited observability, insufficient robustness, and high detection costs by providing comprehensive telemetry, systematic red teaming, and scalable, two-tier detection. It is designed for large enterprises deploying AI agents at scale, as demonstrated by its deployment at Uber.