Red Team on @Unc1e

You Bought the Hands, Not the Brain: After Analyzing Burp AT, I Built an Open-Source Burp MCP

Wed, 12 Aug 2026 00:20:00 +0800

Burp AT proves that penetration testing can be handed to AI, but it locks the model in the cloud and suffers from approval fatigue in production. I analyzed its protocol, followed the official front door, and built an open-source burp-mcp-server — filling the gaps that make or break a red-team automation loop.

Agents Can Now Take Action—Security Can't Stay in the Conversation: Runtime Design at the Action Boundary

Sun, 02 Aug 2026 10:50:39 +0800

Lately I’ve been doing more and more AI red teaming: half the time thinking about how to attack Agents, and the other half thinking about:

once the attacks are done, what should real-world defense actually look like?

I’ve written a local-first Agent Runtime Guard (ARG) myself, and I’ve also taken apart Microsoft’s newly open-sourced Agent Governance Toolkit (AGT). After taking both apart, the conclusion is actually quite clear:

Agent runtime protection is, in essence, the “firewall” of the LLM era. Whenever I mention “firewall”—a word that has been beaten to death—I want to laugh. Still, this is decidedly not another layer of prompt rhetoric, nor is it old IAM renamed. What it intercepts is the segment where “the model’s intent has already formed, but the side effects haven’t happened yet”—the command hasn’t been exec’d, the keys haven’t been read, the email hasn’t been sent, no HTTP has left the network.

Reverse OpenRouter

Sun, 26 Apr 2026 12:10:14 +0800

Reverse-proxy the OpenRouter AI API through an overseas server to work around regional access restrictions.

Background (SCQA)

S - Situation

Overseas AI services (image generation, chat, etc.) are typically accessed through aggregator platforms like OpenRouter that offer a unified API, compatible with the OpenAI SDK.

C - Complication

These services impose access restrictions on mainland China — if the requesting source IP is identified as originating from within China, service is refused outright.

Stuffing OpenAI's Privacy Filter Model into the Red Team Toolchain

Sat, 25 Apr 2026 11:11:28 +0800

Red team security tooling — rebuilding OpenAI’s Privacy Filter into an HTTP gateway for structured PII

extraction

OpenAI open-sourced a small model called Privacy Filter that can identify PII such as names, emails, phone numbers, and addresses from unstructured text.

I spent one evening turning it into an HTTP gateway service, running on an NVIDIA L20, with dual-process inference peaking at 81 RPS and GPU utilization pushed to 98%.

Red Team Essential! Frp Anti-Traceability Enhanced Build

Mon, 14 Apr 2025 21:03:41 +0800

frp is a great tool — high performance, stable, and worth using.

However, its configuration file has gone through two format generations (.ini ->.toml), and the options can be somewhat complicated for newcomers.

When project timelines are tight and workloads heavy, you may not have time to figure out what all these options mean in a short period.

Hence this article — written on April 14, 2025; the currently applicable frp version is: https://github.com/fatedier/frp/releases/tag/v0.61.2

Stable Packet Capture: Intercepting Traffic from Various Devices via a Transparent Proxy (mitmproxy Usage)

Fri, 24 Nov 2023 23:20:13 +0800

Tutorial reference

https://blog.csdn.net/zhuxian1277/article/details/111875951

Use Case

mitmproxy is a powerful man-in-the-middle proxy tool that lets you intercept, view, and modify traffic between clients and servers. Its transparent proxy mode makes mitmproxy extremely useful in specific scenarios, especially when network traffic needs to be analyzed or tested without changing any settings on the target device.

No proxy configuration needed: Unlike Burp Suite, mitmproxy in transparent mode does not require manually setting an HTTP or HTTPS proxy on the target machine. This means the end user or test subject will not notice the proxy’s presence, reducing the chance of human intervention.
Certificate installation: Although no proxy configuration is required in transparent mode, to intercept and decrypt HTTPS traffic you still need to install mitmproxy’s root certificate on the target machine. This is similar to Burp Suite, since both must handle the SSL/TLS handshake to view encrypted traffic.
Via MitmWeb, you can view captured packets locally; in terms of usage it is not much different from Burp.

How to Obtain Source Code During Penetration Testing

Tue, 31 Aug 2021 22:14:19 +0800

Using a recent case, let’s talk about some techniques for obtaining source code in real engagements.

(This is also material from a closed-door sharing session a while back: hope you guys enjoy it~

Liquid Files

Liquid Files is a foreign file-sharing (cloud disk) system; official site: https://www.liquidfiles.com/

It’s a commercial system, widely used abroad.

Today we’ll try to obtain the source code of this system and conduct a preliminary attack-surface assessment (an initial code audit).

[Guest Post] A Commissioned Product Security Test

Thu, 29 Oct 2020 23:06:59 +0800

This article was contributed to the Alibaba Cloud Xianzhi Community. Original content; please cite the source when reposting.

Foreword

On an utterly unremarkable weekend, a buddy of mine messaged me saying he had a product security test on his hands that he couldn’t handle and asked me to help out. I wasn’t keen at first—but Haidilao hotpot is just too good, and so began this commissioned product security test.

Product security testing means using limited resources (time/energy), through security testing and code audit among other means, to uncover as many vulnerabilities as possible, and to leverage these individual findings to drive the developers to fix the product’s security issues.