SuarezPM

Apohara Agentguard

Name: Apohara Agentguard
Author: SuarezPM

AI community

SOURCE https://github.com/SuarezPM/apohara-agentguard

Description

Anti-bypass command-safety hook, local seccomp+Landlock sandbox, and deterministic prompt-injection firewall for Claude Code. Single offline Rust binary, no model.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

apohara-agentguard

**Catch the obfuscated destructive command your agent _runs_ — then confine what it _touches_.**

[![CI](https://img.shields.io/github/actions/workflow/status/SuarezPM/apohara-agentguard/release.yml?style=for-the-badge&label=CI)](https://github.com/SuarezPM/apohara-agentguard/actions) [![License](https://img.shields.io/badge/license-MIT%20OR%20Apache--2.0-blue?style=for-the-badge)](#-license) [![Rust](https://img.shields.io/badge/rust-1.85%2B-orange?style=for-the-badge&logo=rust)](https://www.rust-lang.org) [![Version](https://img.shields.io/badge/version-0.5.1-purple?style=for-the-badge)](https://github.com/SuarezPM/apohara-agentguard/releases) [![Sandbox](https://img.shields.io/badge/sandbox-seccomp%2BLandlock-success?style=for-the-badge)](#-how-it-works--honesty) [![OpenSSF Scorecard](https://api.securityscorecards.dev/projects/github.com/SuarezPM/apohara-agentguard/badge?style=for-the-badge)](https://scorecard.dev/viewer/?uri=github.com/SuarezPM/apohara-agentguard) [![OpenSSF Best Practices](https://www.bestpractices.dev/projects/13128/badge?style=for-the-badge)](https://www.bestpractices.dev/projects/13128)

OpenSSF Passing + Silver criteria mapping: [docs/best-practices-silver.md](docs/best-practices-silver.md)

**[Quick Start](#-quick-start)** · **[Features](#-features)** · **[How it works](#-how-it-works--honesty)** · **[Roadmap](#-roadmap)**

A deterministic, offline Rust safety layer for AI coding agents: an **anti-bypass command gate** that parses Bash structure instead of grepping for substrings, a **seccomp + Landlock sandbox** for the code an agent actually runs, and a **prompt-injection input firewall** — no model, no network at scan time.

Demo: obfuscated destructive commands blo</div> </section> </div> <section class=