Project CodeGuard
Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default practices into AI coding workflows (generation and review). It ships core security rules, translators for popular coding agents, and validators to test rule compliance.
About this tool
Project CodeGuard is an open-source security framework designed to integrate security best practices directly into AI-assisted coding. It provides a comprehensive set of rules covering cryptography (including post-quantum cryptography), secure key management, certificate validation, MFA, OAuth/OIDC, secure session management, and supply chain security (dependency security, SBOM generation, vulnerability management). These rules are translated into formats for popular coding agents, enabling AI assistants to automatically follow security practices when generating or reviewing code. Additionally, it includes validators to test rule compliance, ensuring that generated code meets security standards.