medusa-security
关于
medusa-security is an AI-first security scanner that wraps the Medusa CLI to detect 3,000+ vulnerability patterns, including AI/ML, RAG, and prompt injection risks. It provides structured findings with OWASP mapping and remediation guidance. Use it for comprehensive pre-release scans, rapid AI-focused checks, or targeted scans of changed files during development.
快速安装
Claude Code
推荐npx skills add oimiragieo/agent-studio -a claude-code/plugin add https://github.com/oimiragieo/agent-studiogit clone https://github.com/oimiragieo/agent-studio.git ~/.claude/skills/medusa-security在 Claude Code 中复制并粘贴此命令以安装该技能
GitHub 仓库
Frequently asked questions
What is the medusa-security skill?
medusa-security is a Claude Skill by oimiragieo. Skills package instructions and resources that Claude loads on demand, so Claude can perform medusa-security-related tasks without extra prompting.
How do I install medusa-security?
Use the install commands on this page: add medusa-security to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does medusa-security belong to?
medusa-security is in the security category, tagged security, sast, ai-security, mcp-security, prompt-injection and vulnerability-scanning.
Is medusa-security free to use?
Yes. medusa-security is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
这个Skill为AGENT_SUCCESS_CRITERIA环境变量提供集中化的JSON验证，通过防御性解析防止注入攻击。它确保所有21个CFN Loop代理在测试驱动开发中获得一致的错误处理。开发者只需source验证脚本即可快速集成安全的数据验证功能。
audit-expert 为开发者提供专业级安全审计和合规性评估，支持代码审查、漏洞评估及SOC 2/GDPR等法规合规检查。它结合了多种审计框架（如OWASP ASVS、NIST）和工具（包括Read/Write权限与Bash命令），适用于安全审计、代码审查和基础设施配置检查等场景。开发者可借助该Skill系统化识别安全风险，确保项目符合行业安全标准。
Audit-expert为开发者提供专业级安全审计和合规性检查，支持代码审查、漏洞评估及SOC2/GDPR等标准合规分析。它整合了OWASP ASVS、NIST等安全框架，可执行安全审计、代码审查和基础设施配置检查。开发者可用它自动化安全审查流程，快速识别代码漏洞和合规风险。
这是一个专为安全分析设计的Claude Skill，提供专家级的CodeQL静态代码分析能力，用于漏洞检测和安全扫描。它能指导开发者创建自定义QL查询、分析扫描结果，并集成到CI/CD流程中。该Skill支持多语言项目，帮助开发者在代码层面识别和修复安全风险。