clawguard-self-improving-safety

Official

Autonomously learns and enforces safety.

AuthorSafeAgent-Beihang
Version1.0.0
Installs0

System Documentation

What problem does it solve?

ClawGuard Self-Improving Safety blocks dangerous actions by learning from detected threats and updating its rules automatically to prevent recurrence.

Core Features & Use Cases

  • Standalone enforcement that blocks unsafe commands and credentials
  • Real-time rule learning when integrated with detectors to strengthen defenses
  • Persistent logging of incidents and a CLI to manage rules

Quick Start

Start monitoring threats with the CLI, add new blocking rules as needed, and verify inputs against the active blocklist.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: clawguard-self-improving-safety
Download link: https://github.com/SafeAgent-Beihang/clawguard/archive/main.zip#clawguard-self-improving-safety

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.