chAng-L19

chAng-L19 / codex-redteam-optin-mode

Public

针对于红队攻击思维做出的red team模式(让你的codex像红队一样思考！)，可在单对话使用（可自行适配其他AI）

31
4
100% credibility
Found May 10, 2026 at 31 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

This project provides an opt-in enhancement for a coding AI assistant, enabling specialized, phase-aware guidance for authorized red team security exercises only when explicitly activated.

How It Works

1
🔍 Discover the Security Helper

You hear about a safe add-on that makes your AI coding assistant better at ethical security testing, but only when you choose to turn it on.

2
🛠️ Easy Setup

Follow the quick guide to add the helper to your AI tool, and it blends right in without changing anything.

3
💬 Chat Normally

Start asking your AI questions as usual, and it stays in friendly everyday mode.

4
🔒 Opt In to Expert Mode

When you're doing authorized security work, simply say 'enable red team mode' to unlock specialized guidance.

5
🛡️ Get Tailored Advice

Your AI now spots security phases like web attacks or post-hack steps and gives focused, low-risk tips.

6
❌ Switch Back Anytime

Say 'disable red team mode' to return to normal chatting instantly.

✅ Safer Security Work

You now have a smart, optional boost for legal penetration testing, always under your control.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 31 to 31 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is codex-redteam-optin-mode?

This Python tool turns your Codex AI into a redteam thinker on demand, staying in safe normal mode until you explicitly opt-in with commands like "/redteam on" or "进入红队模式". It detects security phases in your prompts—web exploits, AD attacks, post-exploitation—and injects targeted offensive guidance while respecting OPSEC levels like strict or balanced. Solves the problem of needing redteam-style analysis without polluting everyday coding sessions.

Why is it gaining traction?

Opt-in design prevents accidental redteam slips, unlike always-on jailbreaks, and phase detection auto-tunes advice for web, reverse engineering, or code audits. Cross-platform install script deploys hooks quickly, with validation tests ensuring it runs clean. Devs dig the low-noise, evidence-first prompts that feel like a github red alert for pentests.

Who should use this?

Authorized pentesters scripting redteam playbooks in Codex, security researchers auditing code or binaries, or AD hunters chaining exploits. Ideal for those blending AI with tools like Burp or BloodHound, but skip if you're not cleared for offensive ops.

Verdict

Worth a spin for legal redteam workflows—installs fast, tests pass—but 31 stars and 1.0% credibility signal early-stage maturity; docs stress authorization heavily. Pair with your own validation before production use. (187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.