This project is now maintained by the Coalition for Secure AI (CoSAI).
ā”ļø New Repository: github.com/cosai-oasis/project-codeguard
Please visit the new repository for the latest updates and how to contribute to the project.
rules
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, transla
Description
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.
README
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| v1.2.0 | ## What's Changed * Update README to use 'skills and rules' terminology consistently by @santosomar in https://github.com/project-codeguard/rules/pull/94 * Fix docs formatting for mkdocs rendering by @thomas-bartlett in https://github.com/project-codeguard/rules/pull/95 * Add MCP (Model Context Protocol) security rule based on CoSAI MCP Security Paper: https://www.coalitionforsecureai.org/ve3-whitepaper-ensuring-the-security-governance-and-safety-of-ai-models/ by @santosomar in https://github | Low | 1/27/2026 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
Secure-Agent-LauncherBlock AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.main@2026-04-21
lad_mcp_serverLad MCP Server: Autonomous code & system design review for AI coding agents (Claude Code, Cursor, Codex, etc.). Features multi-model consensus via OpenRouter and context-aware reviews via Serena.main@2026-04-20
E2BOpen-source, secure environment with real-world tools for enterprise-grade agents.@e2b/python-sdk@2.20.0
project-codeguardProject CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices into AI coding agent workflows. It provides comprehensive security rules that guide AI asv1.3.1