AI导哈

测试与安全

slowmist-agent-security-framework

reason-machines/security-skills

Comprehensive security review framework for AI agents to audit skills, repositories, URLs, on-chain addresses, and services in adversarial environments

  • 1114 次安装
  • 12 星标
  • 收录于

安装命令

npx skills add https://github.com/reason-machines/security-skills --skill slowmist-agent-security-framework

SKILL.md

SlowMist Agent Security Framework

Skill by ara.so — Security Skills collection.

A structured security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.

What This Framework Does

SlowMist Agent Security provides:

  • Skill/MCP Installation Review — Detect malicious patterns before installation
  • GitHub Repository Auditing — Security assessment of codebases
  • URL/Document Analysis — Prompt injection and social engineering detection
  • On-Chain Address Review — AML risk assessment and transaction analysis
  • Product/Service Evaluation — Architecture and permission analysis
  • Social Share Review — Validate tools recommended in conversations

Installation

SlowMist Agent Security Framework

Skill by ara.so — Security Skills collection.

A structured security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.

What This Framework Does

SlowMist Agent Security provides:

  • Skill/MCP Installation Review — Detect malicious patterns before installation
  • GitHub Repository Auditing — Security assessment of codebases
  • URL/Document Analysis — Prompt injection and social engineering detection
  • On-Chain Address Review — AML risk assessment and transaction analysis
  • Product/Service Evaluation — Architecture and permission analysis
  • Social Share Review — Validate tools recommended in conversations

Installation

相关 Skills

anthropic-cybersecurity-skillsreason-machines/security-skillsUse 754 structured cybersecurity skills mapped to MITRE ATT&CK, NIST CSF, ATLAS, D3FEND, and NIST AI RMF for AI-driven security operations测试与安全1655pentest-ai-agentsreason-machines/security-skillsClaude Code subagents for offensive security research, penetration testing planning, recon analysis, exploit research, detection engineering, and security reporting测试与安全1364pentest-agents-bug-bounty-frameworkreason-machines/security-skillsAutonomous bug bounty agent framework with 50 agents, hunt loops, exploit chains, MCP servers for platform integration and writeup search智能体工作流1328openosint-ai-osint-frameworkreason-machines/security-skillsAI-powered OSINT agent with interactive REPL, MCP server, and CLI for email/username/domain/IP/phone investigation using 11 integrated tools文档办公1192vibe-security-skillreason-machines/security-skillsAgent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants测试与安全1137openclaw-security-hardeningreason-machines/security-skillsDeploy and manage security hardening for high-privilege autonomous AI agents (OpenClaw) using zero-trust architecture and automated defense matrices测试与安全1129