No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by hzhsec · MCP Server · ★ 51
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AICryptoProxy safe to install? View the security audit →
AICryptoProxy AI 驱动的 Web 加密流量渗透测试自动化代理框架 概述 AICryptoProxy 是一个基于 Claude Code + MCP 的智能渗透测试框架，专为解决前端加密 Web 应用的流量加解密问题而设计。 通过 Claude Code 的 MCP 技能系统，框架能够在几十秒内自动完成传统需要数小时的 JS 逆向分析工作，生成可直接使用的 mitmproxy 加解密代理，配合 Burp Suite 实现无缝的明文操作体验。 核心理念 解决的问题 工作模式 AICryptoProxy 提供两种互补的工作模式，由 Claude Code 的 Skill 自动完成： 模式 A：Direct Crypto（直接加解密） skill:mitmproxy 适用于标准算法、Key 固定的场景。 浏览器 → mitmproxy(:8082)[自动解密] → Burp[:8080] → mitmproxy(:8083)[自动加密] → 服务器 ↑ ↑ ↑ ↑ AI 分析 JS 加密算法 操作明文请求 Burp 修改 AI 生成 Python 加密代码 提取 Key 和 IV 不需要改重放
| Stars | 51 |
| Forks | 6 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 56.7325244417108/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-02 |
| Created | 2026-05-06 |
| Platforms | browser, claude-code, mcp, python |
| Est. Tokens | ~4k |
Explore other popular mcp server tools:
AICryptoProxy is AICryptoProxy 是一个基于 Claude Code(https://claude.ai/code) + MCP(https://docs.claude.ai) 的智能渗透测试框架，专为解决前端加密 Web 应用的流量加解密问题而设计。. It is categorized as a MCP Server with 51 GitHub stars.
AICryptoProxy is primarily written in Python.
You can find installation instructions and usage details in the AICryptoProxy GitHub repository at github.com/hzhsec/AICryptoProxy. The project has 51 stars and 6 forks, indicating an active community.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: