slowmist-agent-security-framework

Official

Secure installs with threat-aware reviews.

AuthorAradotso
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps prevent AI agents from installing or acting on unsafe skills, repositories, URLs, on-chain addresses, and external services by enforcing a verification-first security review workflow.

Core Features & Use Cases

  • Skill/MCP Installation Review: evaluates skills and MCPs for malicious patterns before activation, including obfuscation, credential access, code execution, and network exfiltration risks.
  • GitHub Repository Auditing: assesses repository trust through metadata and evidence-based red-flag scanning, including supply-chain risk considerations.
  • Untrusted Input Analysis (URL/Document, On-Chain, Services): identifies prompt injection, social engineering, and AML/on-chain risk factors, and produces risk-ranked reports to guide safe next actions.

Quick Start

Use the slowmist-agent-security-framework to review a proposed skill installation source and generate a risk level with actionable findings before the agent proceeds.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: slowmist-agent-security-framework
Download link: https://github.com/Aradotso/security-skills/archive/main.zip#slowmist-agent-security-framework

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.