bifrost — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 bifrost-proxy · Codex Skill · ★ 159

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is bifrost safe to install? View the security audit →

About bifrost

Bifrost 高性能 HTTP/HTTPS/SOCKS5 代理服务器 Language: 中文 | English 帮助文档 · English docs · Documentation site Bifrost 是一个用 Rust 编写的高性能,AI 友好的代理服务器,灵感来源于 Whistle。它提供请求拦截、规则修改、TLS 拦截、脚本扩展、流量查看、请求重放以及 Web UI 管理能力。 快速开始 安装 CLI: 方法一:使用脚本安装 该脚本默认会继续安装并信任 CA 证书、安装所有 Bifrost AI skills,并以后台服务启动 Bifrost;安装完成后可直接访问管理端。 Bash 与 PowerShell 安装脚本都会自动探测 GitHub 直连和内置镜像源,优先使用最快可用的 release 下载地址;受限网络中也可通过 指定优先镜像。 安装指定版本 bash curl -fsSL https://raw.githubusercontent.com/bifrost-proxy/bifrost/main/in

agentaiai-toolsbifrost-proxycodexlark-botpostmanproxyproxy-serverrust

Quick Facts

Stars159
Forks24
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score61.4948473664177/100
Open Issues1
Last Updated2026-09-29
Created2026-02-28
Platformscodex, rust
Est. Tokens~23k

Compatible Skills

These tools work well together with bifrost for enhanced workflows:

  • postman-mcp-server — semantic(0.44)+complementary+rare_topics+similar_pop (55%)
  • rust-docs-mcp — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)

bifrost alternative? Top 6 similar tools

Looking for a bifrost alternative? If you're comparing bifrost with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • avibe by avibe-bot · ⭐ 606

    The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex &

  • vibe-remote by cyhhao · ⭐ 450

    Your AI agent army, commanded from Slack/Discord/Telegram/Wechat/Lark. Stream Claude Code, OpenCode, or Codex

  • agnix by agent-sh · ⭐ 439

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • ComfyUI-OpenClaw by rookiestar28 · ⭐ 558

    Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️

  • kindly-web-search-mcp-server by Shelpuk-AI-Technology-Consulting · ⭐ 395

    Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C

  • ClaudeR by IMNMV · ⭐ 346

    Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is bifrost?

bifrost is Bifrost 是一个用 Rust 编写的高性能、AI 友好的代理服务器,它提供强大的请求拦截、修改和规则配置能力,支持 TLS 解密、脚本扩展等高级功能,支持强大的模糊搜索,支持导入导出分享,支持一键重放请求,支持Coding Agent 自主管理。提供类似 postman 的请求管理和验证能力,无缝和代理能力集成。. It is categorized as a Codex Skill with 159 GitHub stars.

What programming language is bifrost written in?

bifrost is primarily written in Rust. It covers topics such as agent, ai, ai-tools.

How do I install or use bifrost?

You can find installation instructions and usage details in the bifrost GitHub repository at github.com/bifrost-proxy/bifrost. The project has 159 stars and 24 forks, indicating an active community.

What license does bifrost use?

bifrost is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to bifrost?

The top alternatives to bifrost on Agent Skills Hub include avibe, vibe-remote, agnix. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools